Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5981 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.5772. Min Act: -0.1700
Data Index: 5833270 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.5772. Min Act: -0.1700
Data Index: 4435935 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.4522. Min Act: -0.1700
Data Index: 743166 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.3897. Min Act: -0.1700
Data Index: 1165015 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.3272. Min Act: -0.1700
Data Index: 8193526 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.3272. Min Act: -0.1700
Data Index: 4879805 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.2647. Min Act: -0.1700
Data Index: 1926360 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.2022. Min Act: -0.1700
Data Index: 6823274 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.2022. Min Act: -0.1700
Data Index: 4782710 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.2647. Min Act: -0.1700
Data Index: 4059264 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.2022. Min Act: -0.1700
Data Index: 4993199 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.1397. Min Act: -0.1700
Data Index: 4326041 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.1397. Min Act: -0.1700
Data Index: 162753 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.1397. Min Act: -0.1700
Data Index: 7637646 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.0772. Min Act: -0.1700
Data Index: 8571398 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.0772. Min Act: -0.1700
Data Index: 295309 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.1397. Min Act: -0.1700
Data Index: 611097 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.0147. Min Act: -0.1700
Data Index: 7498494 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5772. Min Range: -8.5772
Max Act: 7.9522. Min Act: -0.1700
Data Index: 7963120 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5772. Min Range: -8.5772
Max Act: 8.0147. Min Act: -0.1700
Data Index: 809800 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19