Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6192 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.4866. Min Act: -0.1700
Data Index: 8517452 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.4866. Min Act: -0.1700
Data Index: 1694950 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.4241. Min Act: -0.1700
Data Index: 2960181 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.3616. Min Act: -0.1700
Data Index: 2526903 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.2991. Min Act: -0.1700
Data Index: 2281401 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.2991. Min Act: -0.1700
Data Index: 5718108 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.1741. Min Act: -0.1700
Data Index: 1954063 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.1741. Min Act: -0.1700
Data Index: 2574707 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.1741. Min Act: -0.1700
Data Index: 6287533 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.1116. Min Act: -0.1700
Data Index: 2436418 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.1741. Min Act: -0.1700
Data Index: 5838699 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.1116. Min Act: -0.1700
Data Index: 32740 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.0803. Min Act: -0.1700
Data Index: 8324168 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.0803. Min Act: -0.1700
Data Index: 2869984 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.0803. Min Act: -0.1700
Data Index: 204015 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.0803. Min Act: -0.1700
Data Index: 8076425 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.0491. Min Act: -0.1700
Data Index: 4821598 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.0178. Min Act: -0.1700
Data Index: 1741236 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.0491. Min Act: -0.1700
Data Index: 1457670 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4866. Min Range: -8.4866
Max Act: 8.0491. Min Act: -0.1700
Data Index: 5995610 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19