Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5083 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.4526. Min Act: -0.1700
Data Index: 170360 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.2026. Min Act: -0.1700
Data Index: 4864390 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.2339. Min Act: -0.1700
Data Index: 2127312 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.2339. Min Act: -0.1700
Data Index: 2502481 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.1089. Min Act: -0.1700
Data Index: 1247971 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.1089. Min Act: -0.1700
Data Index: 5298550 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0464. Min Act: -0.1700
Data Index: 2170190 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0151. Min Act: -0.1700
Data Index: 4489848 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0151. Min Act: -0.1700
Data Index: 460433 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9526. Min Act: -0.1700
Data Index: 7286948 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9526. Min Act: -0.1700
Data Index: 3203001 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9214. Min Act: -0.1700
Data Index: 8029356 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8901. Min Act: -0.1700
Data Index: 4349323 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8901. Min Act: -0.1700
Data Index: 3724444 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8901. Min Act: -0.1700
Data Index: 5811400 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8901. Min Act: -0.1700
Data Index: 7251044 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8589. Min Act: -0.1700
Data Index: 8424525 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8901. Min Act: -0.1700
Data Index: 7051224 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8276. Min Act: -0.1700
Data Index: 187366 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7964. Min Act: -0.1700
Data Index: 6068644 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19