Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2769 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4508. Min Range: -7.4508
Max Act: 7.4508. Min Act: -0.1700
Data Index: 4824192 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4508. Min Range: -7.4508
Max Act: 7.1695. Min Act: -0.1700
Data Index: 4879334 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.8883. Min Act: -0.1700
Data Index: 5249766 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.8570. Min Act: -0.1700
Data Index: 4802247 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.8258. Min Act: -0.1700
Data Index: 4884204 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.7945. Min Act: -0.1700
Data Index: 1274962 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.7633. Min Act: -0.1700
Data Index: 5269646 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.7008. Min Act: -0.1700
Data Index: 6590334 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.6070. Min Act: -0.1700
Data Index: 3851540 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.5758. Min Act: -0.1700
Data Index: 2387143 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.5758. Min Act: -0.1700
Data Index: 4264688 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.5445. Min Act: -0.1700
Data Index: 2248436 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.5758. Min Act: -0.1700
Data Index: 6975642 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.5758. Min Act: -0.1700
Data Index: 1421646 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.5445. Min Act: -0.1700
Data Index: 3964153 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.5445. Min Act: -0.1700
Data Index: 3140352 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.4820. Min Act: -0.1700
Data Index: 2805656 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.5133. Min Act: -0.1700
Data Index: 5081616 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.4820. Min Act: -0.1700
Data Index: 4887659 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4508. Min Range: -7.4508
Max Act: 6.5133. Min Act: -0.1700
Data Index: 7381400 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19