Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2780 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.6598. Min Act: -0.1700
Data Index: 8738463 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.5660. Min Act: -0.1700
Data Index: 6450197 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.5348. Min Act: -0.1700
Data Index: 4567136 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.5035. Min Act: -0.1700
Data Index: 6642452 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.4723. Min Act: -0.1700
Data Index: 1019503 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.4723. Min Act: -0.1700
Data Index: 319057 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.4098. Min Act: -0.1700
Data Index: 6705135 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.4098. Min Act: -0.1700
Data Index: 3087215 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.4098. Min Act: -0.1700
Data Index: 984000 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.3785. Min Act: -0.1700
Data Index: 4800960 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.3785. Min Act: -0.1700
Data Index: 4028056 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.3473. Min Act: -0.1700
Data Index: 5267136 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.3160. Min Act: -0.1700
Data Index: 6097755 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.3473. Min Act: -0.1700
Data Index: 1090774 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.3473. Min Act: -0.1700
Data Index: 6667660 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.3160. Min Act: -0.1700
Data Index: 129848 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.3160. Min Act: -0.1700
Data Index: 6941154 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.3160. Min Act: -0.1700
Data Index: 1659139 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.3160. Min Act: -0.1700
Data Index: 319056 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6598. Min Range: -5.6598
Max Act: 5.3473. Min Act: -0.1700
Data Index: 5892738 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19