Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1508. Min Range: -10.1508
Max Act: 10.1508. Min Act: -0.1700
Data Index: 5948719 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.6508. Min Act: -0.1700
Data Index: 4880243 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.4633. Min Act: -0.1699
Data Index: 238097 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.4633. Min Act: -0.1700
Data Index: 1233463 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.3383. Min Act: -0.1700
Data Index: 6042848 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.2758. Min Act: -0.1700
Data Index: 4703305 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.2133. Min Act: -0.1700
Data Index: 8371314 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.1508. Min Act: -0.1700
Data Index: 125459 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.1508. Min Act: -0.1700
Data Index: 3238372 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.0883. Min Act: -0.1700
Data Index: 5389266 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.0883. Min Act: -0.1700
Data Index: 8167309 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.0258. Min Act: -0.1700
Data Index: 1548131 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.0258. Min Act: -0.1700
Data Index: 4282379 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1508. Min Range: -10.1508
Max Act: 8.9633. Min Act: -0.1700
Data Index: 1985085 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1508. Min Range: -10.1508
Max Act: 8.9633. Min Act: -0.1700
Data Index: 7259534 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1508. Min Range: -10.1508
Max Act: 9.0258. Min Act: -0.1700
Data Index: 7927147 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1508. Min Range: -10.1508
Max Act: 8.9008. Min Act: -0.1700
Data Index: 4903331 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1508. Min Range: -10.1508
Max Act: 8.9008. Min Act: -0.1700
Data Index: 4028479 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1508. Min Range: -10.1508
Max Act: 8.9008. Min Act: -0.1700
Data Index: 4603904 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1508. Min Range: -10.1508
Max Act: 8.9008. Min Act: -0.1700
Data Index: 3311057 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19