Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1511 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.3202. Min Act: -0.1700
Data Index: 7222026 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.2890. Min Act: -0.1700
Data Index: 8360604 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.2577. Min Act: -0.1700
Data Index: 4000591 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.2577. Min Act: -0.1700
Data Index: 1493954 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.2265. Min Act: -0.1700
Data Index: 8254769 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.1640. Min Act: -0.1700
Data Index: 1362073 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.1327. Min Act: -0.1700
Data Index: 4185882 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.1327. Min Act: -0.1700
Data Index: 5406709 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.1015. Min Act: -0.1700
Data Index: 8123173 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.1015. Min Act: -0.1700
Data Index: 310563 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.0702. Min Act: -0.1700
Data Index: 774330 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.0702. Min Act: -0.1700
Data Index: 3175861 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.0390. Min Act: -0.1700
Data Index: 7435757 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.0390. Min Act: -0.1700
Data Index: 4988370 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.0390. Min Act: -0.1700
Data Index: 2841730 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.0077. Min Act: -0.1700
Data Index: 4795178 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.0077. Min Act: -0.1700
Data Index: 3337317 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.9452. Min Act: -0.1700
Data Index: 7996966 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.9765. Min Act: -0.1700
Data Index: 7157015 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.9765. Min Act: -0.1700
Data Index: 4137335 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19