Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2755 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1359. Min Range: -2.1359
Max Act: 2.1359. Min Act: -0.1700
Data Index: 5487778 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.8313. Min Act: -0.1700
Data Index: 2829539 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.8485. Min Act: -0.1700
Data Index: 6485747 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.8313. Min Act: -0.1700
Data Index: 1790014 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.7797. Min Act: -0.1700
Data Index: 349992 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.7452. Min Act: -0.1700
Data Index: 1086431 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.7106. Min Act: -0.1700
Data Index: 4834048 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.6759. Min Act: -0.1700
Data Index: 101592 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.6759. Min Act: -0.1700
Data Index: 2861070 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.6759. Min Act: -0.1700
Data Index: 784093 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.6411. Min Act: -0.1700
Data Index: 2835517 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.6237. Min Act: -0.1700
Data Index: 7603074 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.6411. Min Act: -0.1700
Data Index: 4075631 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.6062. Min Act: -0.1700
Data Index: 5729907 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.6062. Min Act: -0.1700
Data Index: 2626228 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.5888. Min Act: -0.1700
Data Index: 2689473 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.6062. Min Act: -0.1700
Data Index: 7643082 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.6062. Min Act: -0.1700
Data Index: 7840909 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.5888. Min Act: -0.1699
Data Index: 1746291 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1359. Min Range: -2.1359
Max Act: 1.5888. Min Act: -0.1700
Data Index: 971566 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19