Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2271 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.9285. Min Act: -0.1700
Data Index: 2988279 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.8347. Min Act: -0.1700
Data Index: 1601109 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.8035. Min Act: -0.1700
Data Index: 2091677 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.6785. Min Act: -0.1700
Data Index: 2853831 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.6160. Min Act: -0.1700
Data Index: 7529750 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.7097. Min Act: -0.1700
Data Index: 3541207 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.5847. Min Act: -0.1700
Data Index: 7624900 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.5847. Min Act: -0.1700
Data Index: 2089335 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.5222. Min Act: -0.1700
Data Index: 1826695 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.5847. Min Act: -0.1700
Data Index: 5372868 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.4910. Min Act: -0.1700
Data Index: 7142790 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.4597. Min Act: -0.1700
Data Index: 288099 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.4285. Min Act: -0.1700
Data Index: 8077329 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.3972. Min Act: -0.1700
Data Index: 5783807 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.4910. Min Act: -0.1700
Data Index: 8791642 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.3347. Min Act: -0.1700
Data Index: 4277536 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.3347. Min Act: -0.1700
Data Index: 3662940 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.3660. Min Act: -0.1700
Data Index: 5820679 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.3660. Min Act: -0.1700
Data Index: 4420957 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9285. Min Range: -7.9285
Max Act: 7.3035. Min Act: -0.1700
Data Index: 6721381 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19