Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2942 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2420. Min Range: -7.2420
Max Act: 7.2420. Min Act: -0.1700
Data Index: 7552858 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2420. Min Range: -7.2420
Max Act: 7.1795. Min Act: -0.1700
Data Index: 7494720 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2420. Min Range: -7.2420
Max Act: 7.1483. Min Act: -0.1700
Data Index: 5416981 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.8358. Min Act: -0.1700
Data Index: 5855450 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.6795. Min Act: -0.1700
Data Index: 7498941 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.5858. Min Act: -0.1700
Data Index: 5123934 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.5233. Min Act: -0.1700
Data Index: 6394560 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.4608. Min Act: -0.1700
Data Index: 7693881 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.4295. Min Act: -0.1700
Data Index: 375532 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.3670. Min Act: -0.1700
Data Index: 3964627 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.3670. Min Act: -0.1700
Data Index: 3908138 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.3358. Min Act: -0.1700
Data Index: 3555018 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.3358. Min Act: -0.1700
Data Index: 8033686 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.3358. Min Act: -0.1700
Data Index: 1022512 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.2420. Min Act: -0.1700
Data Index: 7623051 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.2420. Min Act: -0.1700
Data Index: 6252870 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.2420. Min Act: -0.1700
Data Index: 674923 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.2108. Min Act: -0.1700
Data Index: 1535795 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.2108. Min Act: -0.1700
Data Index: 6124123 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2420. Min Range: -7.2420
Max Act: 6.2108. Min Act: -0.1700
Data Index: 8794500 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19