Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4807 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0444. Min Range: -6.0444
Max Act: 6.0444. Min Act: -0.1700
Data Index: 7587886 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.8569. Min Act: -0.1700
Data Index: 1079476 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.8257. Min Act: -0.1700
Data Index: 7909187 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.8257. Min Act: -0.1700
Data Index: 8502358 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.7944. Min Act: -0.1700
Data Index: 7909194 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.7319. Min Act: -0.1700
Data Index: 3544771 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.6382. Min Act: -0.1700
Data Index: 792611 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.6069. Min Act: -0.1700
Data Index: 5131631 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.6069. Min Act: -0.1700
Data Index: 4940276 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.5757. Min Act: -0.1700
Data Index: 8291985 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.5444. Min Act: -0.1700
Data Index: 4647594 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.5444. Min Act: -0.1700
Data Index: 5557625 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.5444. Min Act: -0.1700
Data Index: 5557624 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.4819. Min Act: -0.1700
Data Index: 279271 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.5132. Min Act: -0.1700
Data Index: 882647 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.4507. Min Act: -0.1700
Data Index: 3420797 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.4507. Min Act: -0.1700
Data Index: 7909183 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.4194. Min Act: -0.1700
Data Index: 3043158 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.4194. Min Act: -0.1700
Data Index: 7809117 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0444. Min Range: -6.0444
Max Act: 5.3882. Min Act: -0.1700
Data Index: 1929517 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19