Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0145. Min Range: -9.0145
Max Act: 9.0145. Min Act: -0.1700
Data Index: 6068226 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0145. Min Range: -9.0145
Max Act: 8.3270. Min Act: -0.1700
Data Index: 5097436 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0145. Min Range: -9.0145
Max Act: 8.0770. Min Act: -0.1700
Data Index: 6233414 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0145. Min Range: -9.0145
Max Act: 8.0145. Min Act: -0.1700
Data Index: 157536 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.9832. Min Act: -0.1700
Data Index: 395671 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.9832. Min Act: -0.1700
Data Index: 7598291 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.9520. Min Act: -0.1700
Data Index: 7033882 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.8895. Min Act: -0.1700
Data Index: 1466673 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.8270. Min Act: -0.1700
Data Index: 8375549 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.8582. Min Act: -0.1700
Data Index: 4135571 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.7957. Min Act: -0.1700
Data Index: 7395721 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.7957. Min Act: -0.1700
Data Index: 5749257 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.7957. Min Act: -0.1700
Data Index: 7170153 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.7332. Min Act: -0.1700
Data Index: 3902088 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.7332. Min Act: -0.1700
Data Index: 8240686 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.7332. Min Act: -0.1700
Data Index: 6342432 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.7020. Min Act: -0.1700
Data Index: 1741210 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.7332. Min Act: -0.1700
Data Index: 6026366 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.6707. Min Act: -0.1700
Data Index: 5080278 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0145. Min Range: -9.0145
Max Act: 7.6707. Min Act: -0.1700
Data Index: 5606248 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19