Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1645. Min Range: -6.1645
Max Act: 6.1645. Min Act: -0.1700
Data Index: 6085694 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.6957. Min Act: -0.1700
Data Index: 8201180 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1645. Min Range: -6.1645
Max Act: 4.9457. Min Act: -0.1700
Data Index: 8378235 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.5395. Min Act: -0.1700
Data Index: 5510474 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.5707. Min Act: -0.1700
Data Index: 5552679 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1645. Min Range: -6.1645
Max Act: 4.7270. Min Act: -0.1700
Data Index: 8657654 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.6645. Min Act: -0.1700
Data Index: 1297135 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1645. Min Range: -6.1645
Max Act: 4.6957. Min Act: -0.1700
Data Index: 7029679 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.5395. Min Act: -0.1700
Data Index: 3660972 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.1645. Min Act: -0.1700
Data Index: 5477678 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.4457. Min Act: -0.1700
Data Index: 8242786 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1645. Min Range: -6.1645
Max Act: 4.9770. Min Act: -0.1700
Data Index: 8741437 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.0395. Min Act: -0.1700
Data Index: 4000998 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.6957. Min Act: -0.1700
Data Index: 7709036 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.4770. Min Act: -0.1700
Data Index: 4483803 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.4145. Min Act: -0.1700
Data Index: 7779351 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.3207. Min Act: -0.1700
Data Index: 1624312 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1645. Min Range: -6.1645
Max Act: 4.4457. Min Act: -0.1700
Data Index: 5334542 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.8520. Min Act: -0.1700
Data Index: 4109607 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1645. Min Range: -6.1645
Max Act: 5.4457. Min Act: -0.1700
Data Index: 6998607 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19