Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2461 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.7783. Min Act: -0.1700
Data Index: 4661859 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.7158. Min Act: -0.1700
Data Index: 973951 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.7158. Min Act: -0.1700
Data Index: 3829589 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.6845. Min Act: -0.1700
Data Index: 4410272 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.6220. Min Act: -0.1700
Data Index: 7196022 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.6220. Min Act: -0.1700
Data Index: 6594231 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.5283. Min Act: -0.1700
Data Index: 836611 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4970. Min Act: -0.1700
Data Index: 143478 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4658. Min Act: -0.1700
Data Index: 1123357 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4658. Min Act: -0.1700
Data Index: 5223118 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4345. Min Act: -0.1700
Data Index: 2236514 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4345. Min Act: -0.1700
Data Index: 617027 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4345. Min Act: -0.1700
Data Index: 679208 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4345. Min Act: -0.1700
Data Index: 5940507 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4345. Min Act: -0.1700
Data Index: 306479 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4345. Min Act: -0.1700
Data Index: 8198128 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4033. Min Act: -0.1700
Data Index: 416839 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4033. Min Act: -0.1700
Data Index: 7119691 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4033. Min Act: -0.1700
Data Index: 7073070 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7783. Min Range: -5.7783
Max Act: 5.4033. Min Act: -0.1700
Data Index: 524601 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19