Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 907 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.1052. Min Act: -0.1700
Data Index: 799689 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0740. Min Act: -0.1700
Data Index: 953570 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0427. Min Act: -0.1700
Data Index: 6522927 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.9802. Min Act: -0.1700
Data Index: 7974716 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.9489. Min Act: -0.1700
Data Index: 3808418 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.9489. Min Act: -0.1700
Data Index: 2847469 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.9177. Min Act: -0.1700
Data Index: 7650729 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.9177. Min Act: -0.1700
Data Index: 6070990 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8864. Min Act: -0.1700
Data Index: 4579415 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8864. Min Act: -0.1700
Data Index: 6808918 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8708. Min Act: -0.1700
Data Index: 5280905 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8551. Min Act: -0.1700
Data Index: 5150838 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8708. Min Act: -0.1700
Data Index: 7013026 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8551. Min Act: -0.1700
Data Index: 4719852 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8551. Min Act: -0.1700
Data Index: 8345542 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8708. Min Act: -0.1700
Data Index: 5586780 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8395. Min Act: -0.1700
Data Index: 221904 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8395. Min Act: -0.1700
Data Index: 4921206 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8238. Min Act: -0.1700
Data Index: 7251658 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1052. Min Range: -4.1052
Max Act: 3.8238. Min Act: -0.1700
Data Index: 4979311 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19