Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1184 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0427. Min Range: -8.0427
Max Act: 8.0427. Min Act: -0.1700
Data Index: 8420625 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.9802. Min Act: -0.1700
Data Index: 4549018 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.6365. Min Act: -0.1700
Data Index: 4590318 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.6052. Min Act: -0.1700
Data Index: 1593233 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.5115. Min Act: -0.1700
Data Index: 1976098 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.4490. Min Act: -0.1700
Data Index: 126711 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.4490. Min Act: -0.1700
Data Index: 6369691 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.4490. Min Act: -0.1700
Data Index: 424150 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.4490. Min Act: -0.1700
Data Index: 2541123 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.4490. Min Act: -0.1700
Data Index: 4167725 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.3865. Min Act: -0.1700
Data Index: 8499761 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.3865. Min Act: -0.1700
Data Index: 4167722 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.3865. Min Act: -0.1700
Data Index: 2617699 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.3552. Min Act: -0.1700
Data Index: 2868797 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.3240. Min Act: -0.1700
Data Index: 7487584 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.3240. Min Act: -0.1700
Data Index: 5052278 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.2927. Min Act: -0.1700
Data Index: 6925151 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.2927. Min Act: -0.1700
Data Index: 3095507 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.2927. Min Act: -0.1700
Data Index: 30129 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0427. Min Range: -8.0427
Max Act: 7.2927. Min Act: -0.1700
Data Index: 5183625 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19