Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2711 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.4182. Min Act: -0.1700
Data Index: 4780648 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.4182. Min Act: -0.1700
Data Index: 4971536 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.4025. Min Act: -0.1700
Data Index: 1849336 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3868. Min Act: -0.1700
Data Index: 8222853 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3711. Min Act: -0.1700
Data Index: 2880184 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3554. Min Act: -0.1700
Data Index: 4442398 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3397. Min Act: -0.1700
Data Index: 5596573 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3397. Min Act: -0.1700
Data Index: 1198277 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3397. Min Act: -0.1700
Data Index: 6792204 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3241. Min Act: -0.1700
Data Index: 1896935 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3241. Min Act: -0.1700
Data Index: 6736931 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3241. Min Act: -0.1700
Data Index: 7306613 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3241. Min Act: -0.1700
Data Index: 2580170 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3241. Min Act: -0.1700
Data Index: 5613975 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3084. Min Act: -0.1700
Data Index: 94559 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3084. Min Act: -0.1700
Data Index: 942522 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3084. Min Act: -0.1700
Data Index: 6801459 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3084. Min Act: -0.1700
Data Index: 2274159 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3084. Min Act: -0.1700
Data Index: 2736650 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4182. Min Range: -3.4182
Max Act: 3.3084. Min Act: -0.1700
Data Index: 5076799 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19