Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2188 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.8683. Min Act: -0.1700
Data Index: 5847918 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.6495. Min Act: -0.1700
Data Index: 6039522 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.6495. Min Act: -0.1700
Data Index: 1416357 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.6495. Min Act: -0.1700
Data Index: 7543000 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.4933. Min Act: -0.1700
Data Index: 8494264 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.3995. Min Act: -0.1700
Data Index: 1087679 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.3995. Min Act: -0.1700
Data Index: 3879391 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.3683. Min Act: -0.1700
Data Index: 8400917 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.3370. Min Act: -0.1700
Data Index: 5578636 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.3370. Min Act: -0.1700
Data Index: 3978407 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.3370. Min Act: -0.1700
Data Index: 2100346 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.3370. Min Act: -0.1700
Data Index: 4064476 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.2745. Min Act: -0.1700
Data Index: 4823428 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.2745. Min Act: -0.1700
Data Index: 3367692 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.2433. Min Act: -0.1700
Data Index: 6561256 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.2433. Min Act: -0.1700
Data Index: 8655621 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.2433. Min Act: -0.1700
Data Index: 7290145 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.2120. Min Act: -0.1700
Data Index: 7912496 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.2120. Min Act: -0.1700
Data Index: 1099524 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.2120. Min Act: -0.1700
Data Index: 7088373 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19