Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.3332. Min Act: -0.1700
Data Index: 1762214 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.3332. Min Act: -0.1700
Data Index: 8600330 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.3332. Min Act: -0.1700
Data Index: 6071557 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.3332. Min Act: -0.1700
Data Index: 6095848 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.3332. Min Act: -0.1700
Data Index: 7169841 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2707. Min Act: -0.1700
Data Index: 559065 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.3020. Min Act: -0.1700
Data Index: 2670878 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2707. Min Act: -0.1700
Data Index: 5254696 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2707. Min Act: -0.1700
Data Index: 2571902 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2395. Min Act: -0.1700
Data Index: 2117381 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2395. Min Act: -0.1700
Data Index: 3993572 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2395. Min Act: -0.1700
Data Index: 6240127 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2395. Min Act: -0.1700
Data Index: 6513959 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2395. Min Act: -0.1700
Data Index: 5621892 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2082. Min Act: -0.1700
Data Index: 3897806 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2082. Min Act: -0.1700
Data Index: 6207708 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2082. Min Act: -0.1700
Data Index: 430060 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2082. Min Act: -0.1700
Data Index: 961047 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.2082. Min Act: -0.1700
Data Index: 1622549 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3332. Min Range: -5.3332
Max Act: 5.1770. Min Act: -0.1700
Data Index: 6228647 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19