Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6390 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0863. Min Range: -7.0863
Max Act: 7.0863. Min Act: -0.1700
Data Index: 3837410 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0863. Min Range: -7.0863
Max Act: 7.0550. Min Act: -0.1700
Data Index: 6778392 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.9613. Min Act: -0.1700
Data Index: 650255 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.9613. Min Act: -0.1700
Data Index: 7519479 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.8988. Min Act: -0.1700
Data Index: 3074905 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.7113. Min Act: -0.1700
Data Index: 4727223 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.5863. Min Act: -0.1700
Data Index: 2785688 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.6175. Min Act: -0.1700
Data Index: 2368881 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.5863. Min Act: -0.1700
Data Index: 6134898 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.5550. Min Act: -0.1700
Data Index: 5662746 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.5863. Min Act: -0.1700
Data Index: 8634207 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.5238. Min Act: -0.1700
Data Index: 8537181 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.4925. Min Act: -0.1700
Data Index: 6885734 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.4925. Min Act: -0.1700
Data Index: 5937118 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.4613. Min Act: -0.1700
Data Index: 7066858 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.4613. Min Act: -0.1700
Data Index: 7526779 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.3988. Min Act: -0.1700
Data Index: 2874475 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.4300. Min Act: -0.1700
Data Index: 7796087 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.3988. Min Act: -0.1700
Data Index: 8384630 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0863. Min Range: -7.0863
Max Act: 6.3988. Min Act: -0.1700
Data Index: 2759995 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19