Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3234 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.3816. Min Act: -0.1700
Data Index: 8647113 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.3503. Min Act: -0.1700
Data Index: 3175807 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.3191. Min Act: -0.1700
Data Index: 6872583 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.3191. Min Act: -0.1700
Data Index: 6049701 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.2878. Min Act: -0.1700
Data Index: 798557 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.2566. Min Act: -0.1700
Data Index: 3941778 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.2253. Min Act: -0.1700
Data Index: 3952217 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.2253. Min Act: -0.1700
Data Index: 5092365 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.2253. Min Act: -0.1700
Data Index: 8241930 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.1941. Min Act: -0.1700
Data Index: 483961 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.1628. Min Act: -0.1700
Data Index: 4260250 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.1628. Min Act: -0.1700
Data Index: 4646597 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.1628. Min Act: -0.1700
Data Index: 1110539 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.1316. Min Act: -0.1700
Data Index: 4091871 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.1003. Min Act: -0.1700
Data Index: 611393 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.1003. Min Act: -0.1700
Data Index: 4668517 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.1003. Min Act: -0.1700
Data Index: 7486110 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.0691. Min Act: -0.1700
Data Index: 4590226 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.1003. Min Act: -0.1700
Data Index: 7281246 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3816. Min Range: -5.3816
Max Act: 5.1003. Min Act: -0.1700
Data Index: 2298906 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19