Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6164. Min Range: -7.6164
Max Act: 7.6164. Min Act: -0.1700
Data Index: 2080419 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6164. Min Range: -7.6164
Max Act: 7.2414. Min Act: -0.1700
Data Index: 6725221 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.9602. Min Act: -0.1700
Data Index: 1918906 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.9602. Min Act: -0.1700
Data Index: 8596535 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.9289. Min Act: -0.1700
Data Index: 7639656 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.8664. Min Act: -0.1700
Data Index: 8598157 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.8039. Min Act: -0.1700
Data Index: 2970782 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.7414. Min Act: -0.1700
Data Index: 5969788 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.7414. Min Act: -0.1700
Data Index: 3909170 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.6789. Min Act: -0.1700
Data Index: 7540469 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.6164. Min Act: -0.1700
Data Index: 2090188 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.5852. Min Act: -0.1700
Data Index: 4327967 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.5539. Min Act: -0.1700
Data Index: 1669182 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.5539. Min Act: -0.1700
Data Index: 999255 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.5539. Min Act: -0.1700
Data Index: 8247143 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.4914. Min Act: -0.1700
Data Index: 2617885 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.4914. Min Act: -0.1700
Data Index: 2861325 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.4914. Min Act: -0.1700
Data Index: 2568738 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.4914. Min Act: -0.1700
Data Index: 7256495 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6164. Min Range: -7.6164
Max Act: 6.4914. Min Act: -0.1700
Data Index: 7610094 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19