Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7760. Min Range: -8.7760
Max Act: 8.7760. Min Act: -0.1700
Data Index: 4045599 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7760. Min Range: -8.7760
Max Act: 8.4010. Min Act: -0.1700
Data Index: 1517446 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7760. Min Range: -8.7760
Max Act: 8.2760. Min Act: -0.1700
Data Index: 1113657 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7760. Min Range: -8.7760
Max Act: 8.1510. Min Act: -0.1700
Data Index: 3661532 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7760. Min Range: -8.7760
Max Act: 8.1510. Min Act: -0.1700
Data Index: 1950599 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7760. Min Range: -8.7760
Max Act: 8.0885. Min Act: -0.1700
Data Index: 6122656 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7760. Min Range: -8.7760
Max Act: 8.0572. Min Act: -0.1700
Data Index: 8146515 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7760. Min Range: -8.7760
Max Act: 8.0572. Min Act: -0.1700
Data Index: 3661527 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7760. Min Range: -8.7760
Max Act: 8.0260. Min Act: -0.1700
Data Index: 1512470 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7760. Min Range: -8.7760
Max Act: 7.9947. Min Act: -0.1700
Data Index: 4090883 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7760. Min Range: -8.7760
Max Act: 7.9947. Min Act: -0.1700
Data Index: 4772338 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7760. Min Range: -8.7760
Max Act: 8.0260. Min Act: -0.1700
Data Index: 6843277 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7760. Min Range: -8.7760
Max Act: 7.9322. Min Act: -0.1700
Data Index: 112243 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7760. Min Range: -8.7760
Max Act: 7.9322. Min Act: -0.1700
Data Index: 3599189 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7760. Min Range: -8.7760
Max Act: 7.9010. Min Act: -0.1700
Data Index: 3520036 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7760. Min Range: -8.7760
Max Act: 7.9010. Min Act: -0.1700
Data Index: 2879620 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7760. Min Range: -8.7760
Max Act: 7.9010. Min Act: -0.1700
Data Index: 1872766 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7760. Min Range: -8.7760
Max Act: 7.9322. Min Act: -0.1700
Data Index: 1885893 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7760. Min Range: -8.7760
Max Act: 7.8697. Min Act: -0.1700
Data Index: 1883366 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7760. Min Range: -8.7760
Max Act: 7.8385. Min Act: -0.1700
Data Index: 3048211 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19