Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.5746. Min Act: -0.1700
Data Index: 6812910 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.4493. Min Act: -0.1700
Data Index: 5764534 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.4649. Min Act: -0.1700
Data Index: 2944076 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.4649. Min Act: -0.1700
Data Index: 6479282 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.4493. Min Act: -0.1700
Data Index: 5858804 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.4336. Min Act: -0.1700
Data Index: 7573170 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.4336. Min Act: -0.1700
Data Index: 5277756 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.4179. Min Act: -0.1700
Data Index: 3881292 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.4179. Min Act: -0.1700
Data Index: 8352052 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.3866. Min Act: -0.1700
Data Index: 3498816 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.3709. Min Act: -0.1700
Data Index: 2944075 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.3709. Min Act: -0.1700
Data Index: 1539270 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.3552. Min Act: -0.1700
Data Index: 8813458 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.3552. Min Act: -0.1700
Data Index: 1882586 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.3395. Min Act: -0.1700
Data Index: 8082542 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.3238. Min Act: -0.1700
Data Index: 4244965 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.2924. Min Act: -0.1700
Data Index: 2594792 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.2924. Min Act: -0.1700
Data Index: 1981969 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.2767. Min Act: -0.1700
Data Index: 4395434 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5746. Min Range: -3.5746
Max Act: 3.2924. Min Act: -0.1700
Data Index: 7446252 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19