Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0427. Min Range: -9.0427
Max Act: 9.0427. Min Act: -0.1700
Data Index: 3435902 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.9177. Min Act: -0.1700
Data Index: 2128467 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.6677. Min Act: -0.1700
Data Index: 1072814 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.5427. Min Act: -0.1700
Data Index: 6596297 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.4177. Min Act: -0.1700
Data Index: 3497422 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.3552. Min Act: -0.1700
Data Index: 342426 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.1677. Min Act: -0.1700
Data Index: 367459 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.2302. Min Act: -0.1700
Data Index: 1096508 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.1052. Min Act: -0.1700
Data Index: 1571817 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.1052. Min Act: -0.1700
Data Index: 3236795 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.0427. Min Act: -0.1700
Data Index: 786689 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.0427. Min Act: -0.1700
Data Index: 6599443 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.1052. Min Act: -0.1700
Data Index: 8137795 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.0114. Min Act: -0.1700
Data Index: 7528275 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.0114. Min Act: -0.1700
Data Index: 3325370 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0427. Min Range: -9.0427
Max Act: 8.0114. Min Act: -0.1700
Data Index: 8448252 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0427. Min Range: -9.0427
Max Act: 7.9177. Min Act: -0.1700
Data Index: 1352688 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0427. Min Range: -9.0427
Max Act: 7.8864. Min Act: -0.1700
Data Index: 339066 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0427. Min Range: -9.0427
Max Act: 7.9177. Min Act: -0.1700
Data Index: 8558277 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0427. Min Range: -9.0427
Max Act: 7.8864. Min Act: -0.1700
Data Index: 5426088 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19