Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1929 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.7972. Min Act: -0.1700
Data Index: 2963820 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.7972. Min Act: -0.1700
Data Index: 1804881 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.7972. Min Act: -0.1700
Data Index: 37364 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.7347. Min Act: -0.1700
Data Index: 1966136 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.7347. Min Act: -0.1700
Data Index: 37365 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.7034. Min Act: -0.1700
Data Index: 6902561 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.6722. Min Act: -0.1700
Data Index: 3233385 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.6722. Min Act: -0.1700
Data Index: 5930266 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.6722. Min Act: -0.1700
Data Index: 8638057 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.6722. Min Act: -0.1700
Data Index: 8095784 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.6722. Min Act: -0.1700
Data Index: 414703 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.7034. Min Act: -0.1700
Data Index: 619424 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.6722. Min Act: -0.1700
Data Index: 5030762 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.7034. Min Act: -0.1700
Data Index: 7479737 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.6722. Min Act: -0.1700
Data Index: 619425 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.7034. Min Act: -0.1700
Data Index: 1668348 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.6409. Min Act: -0.1700
Data Index: 1205441 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.6409. Min Act: -0.1700
Data Index: 155253 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.6097. Min Act: -0.1700
Data Index: 710084 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7972. Min Range: -4.7972
Max Act: 4.6409. Min Act: -0.1700
Data Index: 2737595 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19