Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4044 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.2972. Min Act: -0.1700
Data Index: 6175575 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.2659. Min Act: -0.1700
Data Index: 3366583 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.2347. Min Act: -0.1700
Data Index: 3880348 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.1722. Min Act: -0.1700
Data Index: 6555656 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.1722. Min Act: -0.1700
Data Index: 2430228 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.0472. Min Act: -0.1700
Data Index: 2890405 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.0472. Min Act: -0.1700
Data Index: 7465328 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.0159. Min Act: -0.1700
Data Index: 4369548 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.0784. Min Act: -0.1700
Data Index: 2745853 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.0472. Min Act: -0.1700
Data Index: 863538 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.0472. Min Act: -0.1700
Data Index: 330767 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2972. Min Range: -7.2972
Max Act: 7.0159. Min Act: -0.1700
Data Index: 211822 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2972. Min Range: -7.2972
Max Act: 6.9847. Min Act: -0.1700
Data Index: 2430229 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2972. Min Range: -7.2972
Max Act: 6.9847. Min Act: -0.1700
Data Index: 7060398 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2972. Min Range: -7.2972
Max Act: 6.9222. Min Act: -0.1700
Data Index: 2611517 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2972. Min Range: -7.2972
Max Act: 6.9222. Min Act: -0.1700
Data Index: 4427267 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2972. Min Range: -7.2972
Max Act: 6.9534. Min Act: -0.1700
Data Index: 1562191 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2972. Min Range: -7.2972
Max Act: 6.9222. Min Act: -0.1700
Data Index: 790187 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2972. Min Range: -7.2972
Max Act: 6.9222. Min Act: -0.1700
Data Index: 5576958 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2972. Min Range: -7.2972
Max Act: 6.8909. Min Act: -0.1700
Data Index: 314625 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19