Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 698 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.3207. Min Act: -0.1700
Data Index: 5961335 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.3050. Min Act: -0.1700
Data Index: 4357977 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.2736. Min Act: -0.1700
Data Index: 1738937 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.2893. Min Act: -0.1700
Data Index: 2467395 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.2578. Min Act: -0.1700
Data Index: 6838598 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.2578. Min Act: -0.1700
Data Index: 6689622 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.2107. Min Act: -0.1700
Data Index: 6445469 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.2107. Min Act: -0.1700
Data Index: 7461679 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1792. Min Act: -0.1700
Data Index: 61620 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1792. Min Act: -0.1700
Data Index: 3626357 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1635. Min Act: -0.1700
Data Index: 7750921 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1635. Min Act: -0.1700
Data Index: 2968776 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1635. Min Act: -0.1700
Data Index: 4913507 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1792. Min Act: -0.1700
Data Index: 1396240 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1478. Min Act: -0.1700
Data Index: 6868633 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1320. Min Act: -0.1700
Data Index: 4987967 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1478. Min Act: -0.1700
Data Index: 4845020 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1320. Min Act: -0.1700
Data Index: 64671 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1320. Min Act: -0.1700
Data Index: 4188214 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3207. Min Range: -3.3207
Max Act: 3.1320. Min Act: -0.1700
Data Index: 5587722 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19