Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 171 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8734. Min Act: -0.1700
Data Index: 3147333 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8734. Min Act: -0.1700
Data Index: 8226527 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8734. Min Act: -0.1700
Data Index: 4134343 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8421. Min Act: -0.1700
Data Index: 8129269 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8421. Min Act: -0.1700
Data Index: 4239881 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8109. Min Act: -0.1700
Data Index: 3147338 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8109. Min Act: -0.1700
Data Index: 3299993 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8109. Min Act: -0.1700
Data Index: 929756 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8109. Min Act: -0.1700
Data Index: 7673389 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8109. Min Act: -0.1700
Data Index: 2995759 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8109. Min Act: -0.1700
Data Index: 6581230 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.8109. Min Act: -0.1700
Data Index: 5336831 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.7796. Min Act: -0.1700
Data Index: 2732227 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.7796. Min Act: -0.1700
Data Index: 1448202 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.7796. Min Act: -0.1700
Data Index: 7988564 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.7796. Min Act: -0.1700
Data Index: 7398014 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.7796. Min Act: -0.1700
Data Index: 727555 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.7483. Min Act: -0.1700
Data Index: 4187429 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.7483. Min Act: -0.1700
Data Index: 3875184 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8734. Min Range: -3.8734
Max Act: 3.7483. Min Act: -0.1700
Data Index: 1589215 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19