Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4773 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.9110. Min Act: -0.1700
Data Index: 7006422 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.7703. Min Act: -0.1700
Data Index: 4136444 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.7390. Min Act: -0.1700
Data Index: 5700547 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.6608. Min Act: -0.1700
Data Index: 5289400 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.6295. Min Act: -0.1700
Data Index: 5596461 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.5669. Min Act: -0.1700
Data Index: 3506415 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.5669. Min Act: -0.1700
Data Index: 4625173 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.4729. Min Act: -0.1700
Data Index: 3420550 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.4729. Min Act: -0.1700
Data Index: 2119895 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.4259. Min Act: -0.1700
Data Index: 3912438 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.4259. Min Act: -0.1700
Data Index: 917502 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.4416. Min Act: -0.1700
Data Index: 7068740 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.4102. Min Act: -0.1700
Data Index: 1520381 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.3946. Min Act: -0.1700
Data Index: 656996 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.3946. Min Act: -0.1700
Data Index: 8377261 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.3789. Min Act: -0.1700
Data Index: 7844508 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.3946. Min Act: -0.1700
Data Index: 7446157 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.3789. Min Act: -0.1700
Data Index: 4782141 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.3632. Min Act: -0.1700
Data Index: 5920900 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9110. Min Range: -3.9110
Max Act: 3.3632. Min Act: -0.1700
Data Index: 5475957 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19