Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 838 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.9854. Min Act: -0.1700
Data Index: 1535066 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.9541. Min Act: -0.1700
Data Index: 8736780 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.9541. Min Act: -0.1700
Data Index: 8585445 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8916. Min Act: -0.1700
Data Index: 985451 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.9229. Min Act: -0.1700
Data Index: 1849140 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8916. Min Act: -0.1700
Data Index: 661062 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8916. Min Act: -0.1700
Data Index: 1512819 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8603. Min Act: -0.1700
Data Index: 7675945 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8291. Min Act: -0.1700
Data Index: 1586743 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8603. Min Act: -0.1700
Data Index: 1405068 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8291. Min Act: -0.1700
Data Index: 4787166 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8134. Min Act: -0.1700
Data Index: 4349043 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8134. Min Act: -0.1700
Data Index: 6671425 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8291. Min Act: -0.1700
Data Index: 5679511 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8134. Min Act: -0.1700
Data Index: 2581290 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8291. Min Act: -0.1700
Data Index: 1155783 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8134. Min Act: -0.1700
Data Index: 5442531 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8291. Min Act: -0.1700
Data Index: 7822237 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.8134. Min Act: -0.1700
Data Index: 4551488 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9854. Min Range: -3.9854
Max Act: 3.7822. Min Act: -0.1700
Data Index: 70362 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19