Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1505 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0166. Min Range: -7.0166
Max Act: 7.0166. Min Act: -0.1700
Data Index: 8094627 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.4853. Min Act: -0.1700
Data Index: 3725128 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.4541. Min Act: -0.1700
Data Index: 2819700 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.4228. Min Act: -0.1700
Data Index: 5721857 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.3603. Min Act: -0.1700
Data Index: 792684 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.3603. Min Act: -0.1700
Data Index: 1275820 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.2978. Min Act: -0.1700
Data Index: 2379224 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.2978. Min Act: -0.1700
Data Index: 999837 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.2353. Min Act: -0.1700
Data Index: 3254821 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.2041. Min Act: -0.1700
Data Index: 5887200 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.2041. Min Act: -0.1700
Data Index: 7972764 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.2041. Min Act: -0.1700
Data Index: 8342487 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.2041. Min Act: -0.1700
Data Index: 4807423 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.1416. Min Act: -0.1700
Data Index: 5561192 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.1103. Min Act: -0.1700
Data Index: 7677569 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.0791. Min Act: -0.1700
Data Index: 5476514 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.0478. Min Act: -0.1700
Data Index: 2443325 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.0791. Min Act: -0.1700
Data Index: 3753672 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.1103. Min Act: -0.1700
Data Index: 6470186 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0166. Min Range: -7.0166
Max Act: 6.0166. Min Act: -0.1700
Data Index: 7142010 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19