Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4677 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2105. Min Range: -7.2105
Max Act: 7.2105. Min Act: -0.1700
Data Index: 3184230 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2105. Min Range: -7.2105
Max Act: 7.0230. Min Act: -0.1700
Data Index: 5104792 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.8980. Min Act: -0.1700
Data Index: 6656696 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.8980. Min Act: -0.1700
Data Index: 8336678 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.8980. Min Act: -0.1700
Data Index: 7219524 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.8042. Min Act: -0.1700
Data Index: 4268200 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.7730. Min Act: -0.1700
Data Index: 4057644 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.7417. Min Act: -0.1700
Data Index: 7269525 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.7105. Min Act: -0.1700
Data Index: 3092622 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.6792. Min Act: -0.1700
Data Index: 2050925 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.6480. Min Act: -0.1700
Data Index: 3082195 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 4330245 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 3948627 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.6480. Min Act: -0.1700
Data Index: 4792945 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.6792. Min Act: -0.1700
Data Index: 8638565 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.6792. Min Act: -0.1700
Data Index: 5925125 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.6480. Min Act: -0.1700
Data Index: 8381683 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 8804702 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 6564948 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2105. Min Range: -7.2105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 6758416 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19