Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.5384. Min Act: -0.1700
Data Index: 4412639 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.5072. Min Act: -0.1700
Data Index: 5075728 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.4759. Min Act: -0.1700
Data Index: 5514986 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.4759. Min Act: -0.1700
Data Index: 1247637 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.4134. Min Act: -0.1700
Data Index: 5378137 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.4134. Min Act: -0.1700
Data Index: 7619447 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3509. Min Act: -0.1700
Data Index: 592081 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3509. Min Act: -0.1700
Data Index: 4886581 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.3509. Min Act: -0.1700
Data Index: 4552713 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.2884. Min Act: -0.1700
Data Index: 1835120 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.2884. Min Act: -0.1700
Data Index: 2666836 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.2572. Min Act: -0.1700
Data Index: 5451494 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.2572. Min Act: -0.1700
Data Index: 6851898 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.2572. Min Act: -0.1700
Data Index: 4347326 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.1947. Min Act: -0.1700
Data Index: 2666835 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.1947. Min Act: -0.1700
Data Index: 5362552 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.1634. Min Act: -0.1700
Data Index: 1234521 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.1947. Min Act: -0.1700
Data Index: 7934546 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.1947. Min Act: -0.1700
Data Index: 3624974 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5384. Min Range: -6.5384
Max Act: 6.1322. Min Act: -0.1700
Data Index: 3784776 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19