Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 237 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.6076. Min Act: -0.1700
Data Index: 8653904 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.4826. Min Act: -0.1700
Data Index: 7404256 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.4826. Min Act: -0.1700
Data Index: 1938631 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.3576. Min Act: -0.1700
Data Index: 6955834 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.4201. Min Act: -0.1700
Data Index: 4172054 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.3576. Min Act: -0.1700
Data Index: 3126494 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.2951. Min Act: -0.1700
Data Index: 1616646 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.2951. Min Act: -0.1700
Data Index: 31189 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.2951. Min Act: -0.1700
Data Index: 6947977 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.2951. Min Act: -0.1700
Data Index: 1970565 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.2326. Min Act: -0.1700
Data Index: 719862 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.2326. Min Act: -0.1700
Data Index: 6126690 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.2326. Min Act: -0.1700
Data Index: 2958512 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.2951. Min Act: -0.1700
Data Index: 274543 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.2326. Min Act: -0.1700
Data Index: 7117753 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.1701. Min Act: -0.1700
Data Index: 2544672 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.1701. Min Act: -0.1700
Data Index: 7149573 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.1076. Min Act: -0.1700
Data Index: 7282927 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.1076. Min Act: -0.1700
Data Index: 8195232 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6076. Min Range: -10.6076
Max Act: 10.0451. Min Act: -0.1700
Data Index: 3491750 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19