Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3314 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.6016. Min Act: -0.1700
Data Index: 7262366 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.5703. Min Act: -0.1700
Data Index: 7602611 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.5391. Min Act: -0.1700
Data Index: 3342842 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.5078. Min Act: -0.1700
Data Index: 3532805 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.5078. Min Act: -0.1700
Data Index: 6231705 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.5078. Min Act: -0.1700
Data Index: 8540935 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.5078. Min Act: -0.1700
Data Index: 7252100 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4766. Min Act: -0.1700
Data Index: 337178 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4766. Min Act: -0.1700
Data Index: 2498385 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4766. Min Act: -0.1700
Data Index: 8334055 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4766. Min Act: -0.1700
Data Index: 6792649 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4453. Min Act: -0.1700
Data Index: 1675851 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4453. Min Act: -0.1700
Data Index: 4784188 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4453. Min Act: -0.1700
Data Index: 4424843 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4766. Min Act: -0.1700
Data Index: 8239144 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4453. Min Act: -0.1700
Data Index: 5975069 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4453. Min Act: -0.1700
Data Index: 1375469 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4453. Min Act: -0.1700
Data Index: 951272 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4453. Min Act: -0.1700
Data Index: 4267304 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6016. Min Range: -4.6016
Max Act: 4.4140. Min Act: -0.1700
Data Index: 2658648 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19