Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2132. Min Range: -8.2132
Max Act: 8.2132. Min Act: -0.1700
Data Index: 8160176 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2132. Min Range: -8.2132
Max Act: 8.0882. Min Act: -0.1700
Data Index: 4237167 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2132. Min Range: -8.2132
Max Act: 8.0882. Min Act: -0.1700
Data Index: 1767275 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2132. Min Range: -8.2132
Max Act: 8.0882. Min Act: -0.1700
Data Index: 1027073 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2132. Min Range: -8.2132
Max Act: 8.0257. Min Act: -0.1700
Data Index: 254209 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.9632. Min Act: -0.1700
Data Index: 3144387 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.9007. Min Act: -0.1700
Data Index: 1158181 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.9007. Min Act: -0.1700
Data Index: 5338755 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.8382. Min Act: -0.1700
Data Index: 4963350 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.7757. Min Act: -0.1700
Data Index: 3830400 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.8382. Min Act: -0.1700
Data Index: 6185761 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.8382. Min Act: -0.1700
Data Index: 7737535 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.8382. Min Act: -0.1700
Data Index: 7548947 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.7757. Min Act: -0.1700
Data Index: 7958757 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.7757. Min Act: -0.1700
Data Index: 230044 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.7757. Min Act: -0.1700
Data Index: 2780952 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.7445. Min Act: -0.1700
Data Index: 592360 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.7757. Min Act: -0.1700
Data Index: 4387682 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.7757. Min Act: -0.1700
Data Index: 3974137 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2132. Min Range: -8.2132
Max Act: 7.7445. Min Act: -0.1700
Data Index: 6775192 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19