Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2570. Min Act: -0.1700
Data Index: 2653241 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2570. Min Act: -0.1700
Data Index: 2934968 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2570. Min Act: -0.1700
Data Index: 738257 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2570. Min Act: -0.1700
Data Index: 4010798 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2570. Min Act: -0.1700
Data Index: 8070573 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2570. Min Act: -0.1700
Data Index: 4713860 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2239. Min Act: -0.1700
Data Index: 298611 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2405. Min Act: -0.1700
Data Index: 4904939 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2405. Min Act: -0.1700
Data Index: 1109054 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2073. Min Act: -0.1700
Data Index: 7876636 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.1907. Min Act: -0.1700
Data Index: 3632750 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2073. Min Act: -0.1700
Data Index: 5697447 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.1907. Min Act: -0.1700
Data Index: 8410886 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2073. Min Act: -0.1673
Data Index: 5110766 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2239. Min Act: -0.1700
Data Index: 6185649 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2073. Min Act: -0.1700
Data Index: 4426474 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.2073. Min Act: -0.1700
Data Index: 2803599 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.1907. Min Act: -0.1700
Data Index: 6746611 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.1907. Min Act: -0.1700
Data Index: 7685523 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2570. Min Range: -2.2570
Max Act: 2.1741. Min Act: -0.1700
Data Index: 6319833 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19