Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2660 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0587. Min Range: -3.0587
Max Act: 3.0587. Min Act: -0.1700
Data Index: 3492617 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0587. Min Range: -3.0587
Max Act: 3.0113. Min Act: -0.1700
Data Index: 4222373 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0587. Min Range: -3.0587
Max Act: 3.0113. Min Act: -0.1700
Data Index: 599998 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9955. Min Act: -0.1700
Data Index: 6935154 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9797. Min Act: -0.1700
Data Index: 574254 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9639. Min Act: -0.1700
Data Index: 238041 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9322. Min Act: -0.1700
Data Index: 2809601 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9164. Min Act: -0.1700
Data Index: 7809070 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9322. Min Act: -0.1700
Data Index: 3518399 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9005. Min Act: -0.1700
Data Index: 4558646 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8847. Min Act: -0.1700
Data Index: 2991241 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8688. Min Act: -0.1700
Data Index: 2177002 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8529. Min Act: -0.1700
Data Index: 7367307 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8211. Min Act: -0.1700
Data Index: 1270693 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8211. Min Act: -0.1700
Data Index: 7935647 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.7893. Min Act: -0.1700
Data Index: 39827 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.7893. Min Act: -0.1700
Data Index: 356965 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8211. Min Act: -0.1700
Data Index: 1947576 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.7893. Min Act: -0.1700
Data Index: 6350484 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.7733. Min Act: -0.1700
Data Index: 2675084 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19