Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.4339. Min Act: -0.1700
Data Index: 610269 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.3089. Min Act: -0.1700
Data Index: 6067590 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.3402. Min Act: -0.1700
Data Index: 1013507 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.2777. Min Act: -0.1700
Data Index: 1556321 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.2152. Min Act: -0.1700
Data Index: 1624731 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1527. Min Act: -0.1700
Data Index: 2571622 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1527. Min Act: -0.1700
Data Index: 479080 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1527. Min Act: -0.1700
Data Index: 4957827 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1527. Min Act: -0.1700
Data Index: 4759694 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1527. Min Act: -0.1700
Data Index: 1013514 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1527. Min Act: -0.1700
Data Index: 6305078 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1839. Min Act: -0.1700
Data Index: 4458316 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1214. Min Act: -0.1700
Data Index: 5044865 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1214. Min Act: -0.1700
Data Index: 1520441 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1214. Min Act: -0.1700
Data Index: 7841174 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1214. Min Act: -0.1700
Data Index: 1693872 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.1214. Min Act: -0.1700
Data Index: 8130027 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.0902. Min Act: -0.1700
Data Index: 8156820 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.0902. Min Act: -0.1700
Data Index: 7426156 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4339. Min Range: -5.4339
Max Act: 5.0902. Min Act: -0.1700
Data Index: 437470 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19