Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.5399. Min Act: -0.1700
Data Index: 2052122 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.5086. Min Act: -0.1700
Data Index: 7813731 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.4461. Min Act: -0.1700
Data Index: 4642648 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.3524. Min Act: -0.1700
Data Index: 3665480 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.3836. Min Act: -0.1700
Data Index: 3578538 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.3211. Min Act: -0.1700
Data Index: 4011565 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.3211. Min Act: -0.1700
Data Index: 2307257 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.2899. Min Act: -0.1700
Data Index: 5860706 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.2586. Min Act: -0.1700
Data Index: 1591269 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.2586. Min Act: -0.1700
Data Index: 3069642 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.2274. Min Act: -0.1700
Data Index: 6085541 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.2274. Min Act: -0.1700
Data Index: 6888162 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.1961. Min Act: -0.1700
Data Index: 2307256 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.2274. Min Act: -0.1700
Data Index: 1971907 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.2274. Min Act: -0.1700
Data Index: 7294655 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.1961. Min Act: -0.1700
Data Index: 145695 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.1961. Min Act: -0.1700
Data Index: 6228695 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.2274. Min Act: -0.1700
Data Index: 2839801 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.1961. Min Act: -0.1700
Data Index: 1682069 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5399. Min Range: -5.5399
Max Act: 5.1649. Min Act: -0.1700
Data Index: 1536160 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19