Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3486. Min Range: -9.3486
Max Act: 9.3486. Min Act: -0.1700
Data Index: 4721485 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.9736. Min Act: -0.1700
Data Index: 7147583 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.7861. Min Act: -0.1700
Data Index: 3995473 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.6611. Min Act: -0.1700
Data Index: 527436 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.5361. Min Act: -0.1700
Data Index: 564311 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.4736. Min Act: -0.1700
Data Index: 4809919 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.5361. Min Act: -0.1700
Data Index: 3011657 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.5361. Min Act: -0.1700
Data Index: 5588326 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.4111. Min Act: -0.1700
Data Index: 8164986 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.4111. Min Act: -0.1700
Data Index: 701427 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.4111. Min Act: -0.1700
Data Index: 6527206 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.4111. Min Act: -0.1700
Data Index: 4108076 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.4111. Min Act: -0.1700
Data Index: 7791640 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.2861. Min Act: -0.1700
Data Index: 89564 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.2861. Min Act: -0.1700
Data Index: 2558959 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.2861. Min Act: -0.1700
Data Index: 855759 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.2861. Min Act: -0.1700
Data Index: 3342118 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.2861. Min Act: -0.1700
Data Index: 7257715 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.2861. Min Act: -0.1700
Data Index: 6734489 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3486. Min Range: -9.3486
Max Act: 8.2236. Min Act: -0.1700
Data Index: 6295007 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19