Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2052 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0386. Min Range: -9.0386
Max Act: 9.0386. Min Act: -0.1700
Data Index: 6960130 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0386. Min Range: -9.0386
Max Act: 9.0386. Min Act: -0.1700
Data Index: 6583351 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.9761. Min Act: -0.1700
Data Index: 8269964 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.9136. Min Act: -0.1700
Data Index: 1316163 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.8511. Min Act: -0.1700
Data Index: 3243099 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.7886. Min Act: -0.1700
Data Index: 3919484 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.6011. Min Act: -0.1700
Data Index: 7763801 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.6011. Min Act: -0.1700
Data Index: 272803 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.6011. Min Act: -0.1700
Data Index: 8326123 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.6011. Min Act: -0.1700
Data Index: 3128704 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.6011. Min Act: -0.1700
Data Index: 1843944 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.6011. Min Act: -0.1700
Data Index: 4306175 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.6011. Min Act: -0.1700
Data Index: 3762391 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.6011. Min Act: -0.1700
Data Index: 1492461 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.5386. Min Act: -0.1700
Data Index: 5749275 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.4761. Min Act: -0.1700
Data Index: 3922347 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.4761. Min Act: -0.1700
Data Index: 4826361 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.4761. Min Act: -0.1700
Data Index: 7620317 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.4761. Min Act: -0.1700
Data Index: 2717875 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0386. Min Range: -9.0386
Max Act: 8.4761. Min Act: -0.1700
Data Index: 5749280 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19