Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3677. Min Range: -7.3677
Max Act: 7.3677. Min Act: -0.1700
Data Index: 2420855 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3677. Min Range: -7.3677
Max Act: 7.3677. Min Act: -0.1700
Data Index: 8685712 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3677. Min Range: -7.3677
Max Act: 7.1802. Min Act: -0.1700
Data Index: 156099 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3677. Min Range: -7.3677
Max Act: 7.0552. Min Act: -0.1700
Data Index: 411831 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.9927. Min Act: -0.1700
Data Index: 7046909 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.9615. Min Act: -0.1700
Data Index: 2424211 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.9302. Min Act: -0.1700
Data Index: 3907795 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.8990. Min Act: -0.1700
Data Index: 6067397 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.8677. Min Act: -0.1700
Data Index: 8411670 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.8677. Min Act: -0.1700
Data Index: 1553150 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.8677. Min Act: -0.1700
Data Index: 4059278 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.8052. Min Act: -0.1700
Data Index: 3892340 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.8365. Min Act: -0.1700
Data Index: 4336109 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.8052. Min Act: -0.1700
Data Index: 7879639 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.7740. Min Act: -0.1700
Data Index: 7486868 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.7740. Min Act: -0.1700
Data Index: 464283 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.7427. Min Act: -0.1700
Data Index: 2574890 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.7427. Min Act: -0.1700
Data Index: 8001828 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.7740. Min Act: -0.1700
Data Index: 5579577 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3677. Min Range: -7.3677
Max Act: 6.7740. Min Act: -0.1700
Data Index: 4215572 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19