Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.2418. Min Act: -0.1700
Data Index: 6017726 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.2418. Min Act: -0.1700
Data Index: 5752974 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.2418. Min Act: -0.1700
Data Index: 4984124 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.2105. Min Act: -0.1700
Data Index: 1705215 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.2105. Min Act: -0.1700
Data Index: 8774586 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1793. Min Act: -0.1700
Data Index: 5750342 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.2105. Min Act: -0.1700
Data Index: 212184 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1168. Min Act: -0.1700
Data Index: 5924495 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1793. Min Act: -0.1700
Data Index: 6444799 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1480. Min Act: -0.1700
Data Index: 6055222 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1168. Min Act: -0.1700
Data Index: 1239509 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1168. Min Act: -0.1700
Data Index: 1328543 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1168. Min Act: -0.1700
Data Index: 7196396 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.0855. Min Act: -0.1700
Data Index: 7316239 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1168. Min Act: -0.1700
Data Index: 7325915 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.0855. Min Act: -0.1700
Data Index: 6904869 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1168. Min Act: -0.1700
Data Index: 6039213 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1168. Min Act: -0.1700
Data Index: 4350381 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1168. Min Act: -0.1700
Data Index: 133403 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2418. Min Range: -5.2418
Max Act: 5.1168. Min Act: -0.1700
Data Index: 562920 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19