Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 719 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5854. Min Act: -0.1700
Data Index: 2546966 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5384. Min Act: -0.1700
Data Index: 1672243 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5228. Min Act: -0.1700
Data Index: 5186636 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5071. Min Act: -0.1700
Data Index: 5027973 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4914. Min Act: -0.1700
Data Index: 3569022 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4601. Min Act: -0.1700
Data Index: 7484478 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4444. Min Act: -0.1700
Data Index: 7874171 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4444. Min Act: -0.1700
Data Index: 4728868 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4288. Min Act: -0.1700
Data Index: 435965 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.3974. Min Act: -0.1700
Data Index: 3762667 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.3974. Min Act: -0.1700
Data Index: 5608465 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.3974. Min Act: -0.1700
Data Index: 6179768 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.3974. Min Act: -0.1700
Data Index: 7741275 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4131. Min Act: -0.1700
Data Index: 5608467 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.3974. Min Act: -0.1700
Data Index: 2355913 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.3974. Min Act: -0.1700
Data Index: 5186638 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.3817. Min Act: -0.1700
Data Index: 1999277 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.3660. Min Act: -0.1700
Data Index: 6179767 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.3817. Min Act: -0.1700
Data Index: 4728862 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.3660. Min Act: -0.1700
Data Index: 5608461 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19