Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.3996. Min Act: -0.1700
Data Index: 7523197 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.3371. Min Act: -0.1700
Data Index: 146550 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.3059. Min Act: -0.1700
Data Index: 6888993 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.2434. Min Act: -0.1700
Data Index: 5063241 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.2434. Min Act: -0.1700
Data Index: 5345930 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.1809. Min Act: -0.1700
Data Index: 3250112 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.1809. Min Act: -0.1700
Data Index: 1833586 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.1496. Min Act: -0.1700
Data Index: 5878445 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.1809. Min Act: -0.1700
Data Index: 3527967 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.1809. Min Act: -0.1700
Data Index: 6241987 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.1184. Min Act: -0.1700
Data Index: 5765382 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.1496. Min Act: -0.1700
Data Index: 6651663 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.1496. Min Act: -0.1700
Data Index: 8675588 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.0871. Min Act: -0.1700
Data Index: 7332686 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.1184. Min Act: -0.1700
Data Index: 3175011 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.0871. Min Act: -0.1700
Data Index: 7111939 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.0871. Min Act: -0.1700
Data Index: 7631534 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.0871. Min Act: -0.1700
Data Index: 8315314 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.0871. Min Act: -0.1700
Data Index: 4324022 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3996. Min Range: -4.3996
Max Act: 4.0871. Min Act: -0.1700
Data Index: 166574 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19