Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6391 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1539. Min Range: -9.1539
Max Act: 9.1539. Min Act: -0.1700
Data Index: 3192863 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.9664. Min Act: -0.1700
Data Index: 3192862 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.7789. Min Act: -0.1700
Data Index: 3032561 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.7789. Min Act: -0.1700
Data Index: 5203434 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.5914. Min Act: -0.1700
Data Index: 6381871 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.5289. Min Act: -0.1700
Data Index: 1205125 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.5914. Min Act: -0.1700
Data Index: 3032557 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.5289. Min Act: -0.1700
Data Index: 8417568 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.5289. Min Act: -0.1700
Data Index: 1205126 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.4664. Min Act: -0.1700
Data Index: 2976671 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.3414. Min Act: -0.1700
Data Index: 3271564 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.3414. Min Act: -0.1700
Data Index: 6141361 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.3414. Min Act: -0.1700
Data Index: 3192861 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.3414. Min Act: -0.1700
Data Index: 2266601 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.3414. Min Act: -0.1700
Data Index: 2976672 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.3414. Min Act: -0.1700
Data Index: 6141366 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.2789. Min Act: -0.1700
Data Index: 3032562 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.2789. Min Act: -0.1700
Data Index: 6141360 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.2164. Min Act: -0.1700
Data Index: 3589109 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1539. Min Range: -9.1539
Max Act: 8.2164. Min Act: -0.1700
Data Index: 5904584 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19