Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5714 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.7576. Min Act: -0.1700
Data Index: 8253265 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.6326. Min Act: -0.1700
Data Index: 5237355 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.5388. Min Act: -0.1700
Data Index: 8170511 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.5076. Min Act: -0.1700
Data Index: 8736527 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.4763. Min Act: -0.1700
Data Index: 7844576 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.4451. Min Act: -0.1700
Data Index: 4114216 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.3826. Min Act: -0.1700
Data Index: 5791135 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.3826. Min Act: -0.1700
Data Index: 8638326 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.3513. Min Act: -0.1700
Data Index: 3061189 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.3513. Min Act: -0.1700
Data Index: 6161234 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.3201. Min Act: -0.1700
Data Index: 8797009 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.2888. Min Act: -0.1700
Data Index: 8199346 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.2576. Min Act: -0.1700
Data Index: 5709979 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.2263. Min Act: -0.1700
Data Index: 4961323 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.1951. Min Act: -0.1700
Data Index: 622079 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.2263. Min Act: -0.1700
Data Index: 8574300 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.2263. Min Act: -0.1700
Data Index: 3886375 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.2263. Min Act: -0.1700
Data Index: 8076589 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.2263. Min Act: -0.1700
Data Index: 2154364 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7576. Min Range: -6.7576
Max Act: 6.1951. Min Act: -0.1700
Data Index: 1597894 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19