Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5478 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0660. Min Range: -4.0660
Max Act: 4.0660. Min Act: -0.1700
Data Index: 8325196 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.8784. Min Act: -0.1700
Data Index: 7513584 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.8471. Min Act: -0.1700
Data Index: 779990 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.8315. Min Act: -0.1700
Data Index: 1286224 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.7846. Min Act: -0.1700
Data Index: 2468206 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.7846. Min Act: -0.1700
Data Index: 4003922 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.7220. Min Act: -0.1700
Data Index: 7165826 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.7220. Min Act: -0.1700
Data Index: 1018247 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.7064. Min Act: -0.1700
Data Index: 4446747 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.6908. Min Act: -0.1700
Data Index: 593134 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.6908. Min Act: -0.1700
Data Index: 7919536 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.6595. Min Act: -0.1700
Data Index: 7247863 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.6125. Min Act: -0.1700
Data Index: 7518987 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.6282. Min Act: -0.1700
Data Index: 8617184 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.6125. Min Act: -0.1700
Data Index: 2337949 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.6125. Min Act: -0.1700
Data Index: 7409052 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.6282. Min Act: -0.1700
Data Index: 3329088 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.5969. Min Act: -0.1700
Data Index: 792780 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.5969. Min Act: -0.1700
Data Index: 8175085 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0660. Min Range: -4.0660
Max Act: 3.5812. Min Act: -0.1700
Data Index: 975178 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19