Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2812 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.5539. Min Act: -0.1700
Data Index: 2044186 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.3977. Min Act: -0.1700
Data Index: 1649755 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.3664. Min Act: -0.1700
Data Index: 2915492 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.3352. Min Act: -0.1700
Data Index: 53786 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.3039. Min Act: -0.1700
Data Index: 8724432 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.2727. Min Act: -0.1700
Data Index: 4011155 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.2727. Min Act: -0.1700
Data Index: 6609758 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.2414. Min Act: -0.1700
Data Index: 6290837 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.2414. Min Act: -0.1700
Data Index: 3221107 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.2102. Min Act: -0.1700
Data Index: 385848 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.1789. Min Act: -0.1700
Data Index: 4011148 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.2102. Min Act: -0.1700
Data Index: 6074077 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.1789. Min Act: -0.1700
Data Index: 95693 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.1789. Min Act: -0.1700
Data Index: 3625517 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.1789. Min Act: -0.1700
Data Index: 2615719 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.1789. Min Act: -0.1700
Data Index: 3195254 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.1477. Min Act: -0.1700
Data Index: 5454864 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.1477. Min Act: -0.1700
Data Index: 375231 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.1477. Min Act: -0.1700
Data Index: 1297833 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5539. Min Range: -4.5539
Max Act: 4.1477. Min Act: -0.1700
Data Index: 5894844 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19