Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5147 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0959. Min Range: -6.0959
Max Act: 6.0959. Min Act: -0.1700
Data Index: 8122850 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0959. Min Range: -6.0959
Max Act: 6.0022. Min Act: -0.1700
Data Index: 6667895 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0959. Min Range: -6.0959
Max Act: 6.0022. Min Act: -0.1700
Data Index: 4140100 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.9709. Min Act: -0.1700
Data Index: 1105282 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.9709. Min Act: -0.1700
Data Index: 4381286 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.9709. Min Act: -0.1700
Data Index: 3669793 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.9397. Min Act: -0.1700
Data Index: 2366758 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.8772. Min Act: -0.1700
Data Index: 8499924 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.9084. Min Act: -0.1700
Data Index: 4764854 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.9084. Min Act: -0.1700
Data Index: 7304810 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.9084. Min Act: -0.1700
Data Index: 6379717 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.9084. Min Act: -0.1700
Data Index: 7926180 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.8459. Min Act: -0.1700
Data Index: 8184131 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.8459. Min Act: -0.1700
Data Index: 6838688 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.8772. Min Act: -0.1700
Data Index: 3676582 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.8772. Min Act: -0.1700
Data Index: 6085526 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.8459. Min Act: -0.1700
Data Index: 8386616 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.8147. Min Act: -0.1700
Data Index: 84540 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.8147. Min Act: -0.1700
Data Index: 4360042 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0959. Min Range: -6.0959
Max Act: 5.7834. Min Act: -0.1700
Data Index: 658995 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19