Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5419 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3288. Min Range: -10.3288
Max Act: 10.3288. Min Act: -0.1700
Data Index: 4257839 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3288. Min Range: -10.3288
Max Act: 10.0788. Min Act: -0.1700
Data Index: 1958401 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.9538. Min Act: -0.1700
Data Index: 7110104 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.8288. Min Act: -0.1700
Data Index: 3022396 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.8288. Min Act: -0.1700
Data Index: 5228649 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.8288. Min Act: -0.1700
Data Index: 4542962 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.7663. Min Act: -0.1700
Data Index: 1475957 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.7663. Min Act: -0.1700
Data Index: 3654511 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.7038. Min Act: -0.1700
Data Index: 5675472 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.7038. Min Act: -0.1700
Data Index: 8638929 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.7038. Min Act: -0.1700
Data Index: 3364297 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.6413. Min Act: -0.1700
Data Index: 8540540 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.6413. Min Act: -0.1700
Data Index: 1652538 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.6413. Min Act: -0.1700
Data Index: 988037 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.6413. Min Act: -0.1700
Data Index: 7741675 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.6413. Min Act: -0.1700
Data Index: 2393065 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.6413. Min Act: -0.1700
Data Index: 6162370 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.6413. Min Act: -0.1700
Data Index: 925767 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.6413. Min Act: -0.1700
Data Index: 7298916 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3288. Min Range: -10.3288
Max Act: 9.5788. Min Act: -0.1700
Data Index: 803023 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19