Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3172 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2406. Min Range: -4.2406
Max Act: 4.2406. Min Act: -0.1700
Data Index: 4728410 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2406. Min Range: -4.2406
Max Act: 4.0530. Min Act: -0.1700
Data Index: 4728420 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2406. Min Range: -4.2406
Max Act: 4.0530. Min Act: -0.1700
Data Index: 6525807 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.9905. Min Act: -0.1700
Data Index: 593749 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.9905. Min Act: -0.1700
Data Index: 1602976 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.9905. Min Act: -0.1700
Data Index: 3171302 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.9593. Min Act: -0.1700
Data Index: 2965841 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.9905. Min Act: -0.1700
Data Index: 4195212 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.9593. Min Act: -0.1700
Data Index: 4852818 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.9280. Min Act: -0.1700
Data Index: 7762583 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.9280. Min Act: -0.1700
Data Index: 6425199 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.9280. Min Act: -0.1700
Data Index: 4195211 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.8967. Min Act: -0.1700
Data Index: 337808 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.8655. Min Act: -0.1700
Data Index: 4725906 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.9280. Min Act: -0.1700
Data Index: 4728422 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.8655. Min Act: -0.1700
Data Index: 4728421 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.8967. Min Act: -0.1700
Data Index: 4728419 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.8967. Min Act: -0.1700
Data Index: 2938530 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.8967. Min Act: -0.1700
Data Index: 6238084 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2406. Min Range: -4.2406
Max Act: 3.8967. Min Act: -0.1700
Data Index: 5049100 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19