Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.5688. Min Act: -0.1700
Data Index: 5875599 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.4438. Min Act: -0.1700
Data Index: 5008232 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.3813. Min Act: -0.1700
Data Index: 2866810 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.3813. Min Act: -0.1700
Data Index: 4211533 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.3501. Min Act: -0.1700
Data Index: 992129 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.2251. Min Act: -0.1700
Data Index: 7559652 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.2876. Min Act: -0.1700
Data Index: 762924 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.3188. Min Act: -0.1700
Data Index: 3570543 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.2251. Min Act: -0.1700
Data Index: 3438325 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.2251. Min Act: -0.1700
Data Index: 4504542 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.1938. Min Act: -0.1700
Data Index: 1389573 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.1626. Min Act: -0.1700
Data Index: 6647730 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.1001. Min Act: -0.1700
Data Index: 2545089 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.1001. Min Act: -0.1700
Data Index: 2953523 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.1001. Min Act: -0.1700
Data Index: 2573036 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.0688. Min Act: -0.1700
Data Index: 7761235 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.0688. Min Act: -0.1700
Data Index: 8699957 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.0688. Min Act: -0.1700
Data Index: 3719334 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.0688. Min Act: -0.1700
Data Index: 4281835 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5688. Min Range: -6.5688
Max Act: 6.0376. Min Act: -0.1700
Data Index: 3124911 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19