Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2504 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5102. Min Range: -6.5102
Max Act: 6.5102. Min Act: -0.1700
Data Index: 4535084 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5102. Min Range: -6.5102
Max Act: 6.1977. Min Act: -0.1700
Data Index: 7012488 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5102. Min Range: -6.5102
Max Act: 6.1352. Min Act: -0.1700
Data Index: 5815712 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5102. Min Range: -6.5102
Max Act: 6.1039. Min Act: -0.1700
Data Index: 5785603 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5102. Min Range: -6.5102
Max Act: 6.0414. Min Act: -0.1700
Data Index: 4619345 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5102. Min Range: -6.5102
Max Act: 6.0414. Min Act: -0.1700
Data Index: 8737482 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5102. Min Range: -6.5102
Max Act: 6.0102. Min Act: -0.1700
Data Index: 8523853 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5102. Min Range: -6.5102
Max Act: 6.0102. Min Act: -0.1700
Data Index: 635881 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5102. Min Range: -6.5102
Max Act: 6.0102. Min Act: -0.1700
Data Index: 2936650 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5102. Min Range: -6.5102
Max Act: 6.0102. Min Act: -0.1700
Data Index: 490731 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5102. Min Range: -6.5102
Max Act: 5.9477. Min Act: -0.1700
Data Index: 1916414 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5102. Min Range: -6.5102
Max Act: 5.9477. Min Act: -0.1700
Data Index: 1242422 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5102. Min Range: -6.5102
Max Act: 5.9164. Min Act: -0.1700
Data Index: 3550110 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5102. Min Range: -6.5102
Max Act: 5.9164. Min Act: -0.1700
Data Index: 2282935 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5102. Min Range: -6.5102
Max Act: 5.8852. Min Act: -0.1700
Data Index: 8562774 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5102. Min Range: -6.5102
Max Act: 5.8539. Min Act: -0.1700
Data Index: 3367465 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5102. Min Range: -6.5102
Max Act: 5.8539. Min Act: -0.1700
Data Index: 8449155 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5102. Min Range: -6.5102
Max Act: 5.8227. Min Act: -0.1700
Data Index: 8618075 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5102. Min Range: -6.5102
Max Act: 5.8852. Min Act: -0.1700
Data Index: 3916467 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5102. Min Range: -6.5102
Max Act: 5.8227. Min Act: -0.1700
Data Index: 4121781 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19