Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.7633. Min Act: -0.1700
Data Index: 5825187 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.6071. Min Act: -0.1700
Data Index: 6010585 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.6071. Min Act: -0.1700
Data Index: 3499542 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.6383. Min Act: -0.1700
Data Index: 4259617 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.5758. Min Act: -0.1700
Data Index: 6362563 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.5446. Min Act: -0.1700
Data Index: 1042408 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.5758. Min Act: -0.1700
Data Index: 4699559 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.4821. Min Act: -0.1700
Data Index: 233789 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.4508. Min Act: -0.1700
Data Index: 20908 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.4196. Min Act: -0.1700
Data Index: 3851214 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.4196. Min Act: -0.1700
Data Index: 5732657 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.3883. Min Act: -0.1700
Data Index: 830679 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.3883. Min Act: -0.1700
Data Index: 4673805 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.3883. Min Act: -0.1700
Data Index: 6362564 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.3883. Min Act: -0.1700
Data Index: 7809020 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.3571. Min Act: -0.1700
Data Index: 801447 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.3571. Min Act: -0.1700
Data Index: 6159527 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.3883. Min Act: -0.1700
Data Index: 2305849 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.3571. Min Act: -0.1700
Data Index: 5732656 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7633. Min Range: -5.7633
Max Act: 5.3571. Min Act: -0.1700
Data Index: 1665516 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19