Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6291. Min Range: -7.6291
Max Act: 7.6291. Min Act: -0.1700
Data Index: 8276939 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6291. Min Range: -7.6291
Max Act: 7.5041. Min Act: -0.1700
Data Index: 3826652 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6291. Min Range: -7.6291
Max Act: 7.1916. Min Act: -0.1700
Data Index: 2297568 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6291. Min Range: -7.6291
Max Act: 7.1291. Min Act: -0.1700
Data Index: 8158807 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.8791. Min Act: -0.1700
Data Index: 8729316 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.7541. Min Act: -0.1700
Data Index: 837816 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.6603. Min Act: -0.1700
Data Index: 542759 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.6916. Min Act: -0.1700
Data Index: 6862969 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.6291. Min Act: -0.1700
Data Index: 6683971 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.5978. Min Act: -0.1700
Data Index: 4361651 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.5978. Min Act: -0.1700
Data Index: 6594280 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.5041. Min Act: -0.1700
Data Index: 5727979 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.3791. Min Act: -0.1700
Data Index: 8152028 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.4103. Min Act: -0.1700
Data Index: 7011357 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.3791. Min Act: -0.1700
Data Index: 5345148 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.4103. Min Act: -0.1700
Data Index: 7889237 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.3478. Min Act: -0.1700
Data Index: 577581 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.3791. Min Act: -0.1700
Data Index: 8085042 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.3791. Min Act: -0.1700
Data Index: 6496207 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6291. Min Range: -7.6291
Max Act: 6.3478. Min Act: -0.1700
Data Index: 6208787 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19