Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 820 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.9989. Min Act: -0.1700
Data Index: 8067639 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.9677. Min Act: -0.1700
Data Index: 3474347 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.9677. Min Act: -0.1700
Data Index: 6057023 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.8114. Min Act: -0.1700
Data Index: 7375882 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.8114. Min Act: -0.1700
Data Index: 346455 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.8114. Min Act: -0.1700
Data Index: 3549672 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.7802. Min Act: -0.1700
Data Index: 5665496 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.8114. Min Act: -0.1700
Data Index: 5968588 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.7177. Min Act: -0.1700
Data Index: 6564140 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.6864. Min Act: -0.1700
Data Index: 6222130 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.6552. Min Act: -0.1700
Data Index: 7459497 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.5927. Min Act: -0.1700
Data Index: 2648022 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.6239. Min Act: -0.1700
Data Index: 321129 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.5927. Min Act: -0.1700
Data Index: 2504074 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.5614. Min Act: -0.1700
Data Index: 2859847 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.5614. Min Act: -0.1700
Data Index: 7911241 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.5614. Min Act: -0.1700
Data Index: 4902221 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.5614. Min Act: -0.1700
Data Index: 2487621 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.5302. Min Act: -0.1700
Data Index: 7146563 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9989. Min Range: -5.9989
Max Act: 5.5302. Min Act: -0.1700
Data Index: 3051367 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19