Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.5059. Min Act: -0.1700
Data Index: 7286372 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.4434. Min Act: -0.1700
Data Index: 5866316 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.3809. Min Act: -0.1700
Data Index: 3536349 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.3497. Min Act: -0.1700
Data Index: 7876690 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.3184. Min Act: -0.1700
Data Index: 5692951 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.2872. Min Act: -0.1700
Data Index: 296877 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.3184. Min Act: -0.1700
Data Index: 7426339 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.2872. Min Act: -0.1700
Data Index: 5879609 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.2559. Min Act: -0.1700
Data Index: 7451145 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.2247. Min Act: -0.1700
Data Index: 1442957 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.1934. Min Act: -0.1700
Data Index: 1538637 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.2247. Min Act: -0.1700
Data Index: 330246 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.1934. Min Act: -0.1700
Data Index: 6678299 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.1622. Min Act: -0.1700
Data Index: 6842495 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.1622. Min Act: -0.1700
Data Index: 1487307 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.1622. Min Act: -0.1700
Data Index: 6828334 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.0997. Min Act: -0.1700
Data Index: 6651517 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.1309. Min Act: -0.1700
Data Index: 8554906 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.0997. Min Act: -0.1700
Data Index: 3222597 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5059. Min Range: -6.5059
Max Act: 6.0684. Min Act: -0.1700
Data Index: 6326233 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19