Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.5266. Min Act: -0.1700
Data Index: 8467793 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.4953. Min Act: -0.1700
Data Index: 7629291 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.3078. Min Act: -0.1700
Data Index: 5478229 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.3078. Min Act: -0.1700
Data Index: 2578004 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.3078. Min Act: -0.1700
Data Index: 7793173 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.2766. Min Act: -0.1700
Data Index: 8743820 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.2766. Min Act: -0.1700
Data Index: 4573951 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.3078. Min Act: -0.1700
Data Index: 8705742 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.2141. Min Act: -0.1700
Data Index: 3352948 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.2141. Min Act: -0.1700
Data Index: 6989998 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.1516. Min Act: -0.1700
Data Index: 1804725 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.1828. Min Act: -0.1700
Data Index: 6853073 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.1203. Min Act: -0.1700
Data Index: 5100570 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.1203. Min Act: -0.1700
Data Index: 5851661 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.1203. Min Act: -0.1700
Data Index: 3735608 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.1203. Min Act: -0.1700
Data Index: 4705822 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.0890. Min Act: -0.1700
Data Index: 4480136 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.1203. Min Act: -0.1700
Data Index: 4185477 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.0890. Min Act: -0.1700
Data Index: 6745685 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5266. Min Range: -4.5266
Max Act: 4.0890. Min Act: -0.1700
Data Index: 1742981 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19