Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1139 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.6549. Min Act: -0.1700
Data Index: 5080333 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.6236. Min Act: -0.1700
Data Index: 7364455 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.5299. Min Act: -0.1700
Data Index: 5615728 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.5299. Min Act: -0.1700
Data Index: 7572332 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.4986. Min Act: -0.1700
Data Index: 7754719 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.4674. Min Act: -0.1700
Data Index: 698551 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.4049. Min Act: -0.1700
Data Index: 3105772 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.4049. Min Act: -0.1700
Data Index: 69696 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.4049. Min Act: -0.1700
Data Index: 1555471 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.3111. Min Act: -0.1700
Data Index: 6635756 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.3111. Min Act: -0.1700
Data Index: 6756855 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.3424. Min Act: -0.1700
Data Index: 3580707 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.3424. Min Act: -0.1700
Data Index: 1852651 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.3111. Min Act: -0.1700
Data Index: 2830476 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.3111. Min Act: -0.1700
Data Index: 1462833 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.3111. Min Act: -0.1700
Data Index: 4933655 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.3111. Min Act: -0.1700
Data Index: 2496375 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.3111. Min Act: -0.1700
Data Index: 74765 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.2799. Min Act: -0.1700
Data Index: 4626508 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6549. Min Range: -6.6549
Max Act: 6.2799. Min Act: -0.1700
Data Index: 1462835 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19