Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3161 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.3419. Min Act: -0.1700
Data Index: 6307942 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.2794. Min Act: -0.1700
Data Index: 3374520 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.3107. Min Act: -0.1700
Data Index: 2378994 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.2794. Min Act: -0.1700
Data Index: 3534157 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.2482. Min Act: -0.1700
Data Index: 2684883 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.2169. Min Act: -0.1700
Data Index: 5043089 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.2482. Min Act: -0.1700
Data Index: 2518833 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.1857. Min Act: -0.1700
Data Index: 5330563 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.1857. Min Act: -0.1700
Data Index: 3128250 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.1544. Min Act: -0.1700
Data Index: 3510916 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.1544. Min Act: -0.1700
Data Index: 4836536 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.1544. Min Act: -0.1700
Data Index: 1096720 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.1544. Min Act: -0.1700
Data Index: 1263597 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.1544. Min Act: -0.1700
Data Index: 1822110 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.1544. Min Act: -0.1700
Data Index: 8362144 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.0919. Min Act: -0.1700
Data Index: 5860960 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.1232. Min Act: -0.1700
Data Index: 2244393 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.1232. Min Act: -0.1700
Data Index: 4019726 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.1232. Min Act: -0.1700
Data Index: 2518832 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3419. Min Range: -5.3419
Max Act: 5.0607. Min Act: -0.1700
Data Index: 2305463 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19