Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5333 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.2095. Min Act: -0.1700
Data Index: 1791621 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.2095. Min Act: -0.1700
Data Index: 146690 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.1782. Min Act: -0.1700
Data Index: 4311821 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.1782. Min Act: -0.1700
Data Index: 8779076 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.1470. Min Act: -0.1700
Data Index: 2305410 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.1470. Min Act: -0.1700
Data Index: 5079594 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0845. Min Act: -0.1700
Data Index: 4069922 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0532. Min Act: -0.1700
Data Index: 4077539 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0532. Min Act: -0.1700
Data Index: 7814209 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0532. Min Act: -0.1700
Data Index: 4916894 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0532. Min Act: -0.1700
Data Index: 4574418 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0532. Min Act: -0.1700
Data Index: 2325693 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0532. Min Act: -0.1700
Data Index: 970179 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0220. Min Act: -0.1700
Data Index: 4111736 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0220. Min Act: -0.1700
Data Index: 3539402 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0220. Min Act: -0.1700
Data Index: 6966469 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0220. Min Act: -0.1700
Data Index: 8792777 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2095. Min Range: -5.2095
Max Act: 4.9907. Min Act: -0.1700
Data Index: 7345861 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0220. Min Act: -0.1700
Data Index: 4806397 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2095. Min Range: -5.2095
Max Act: 5.0220. Min Act: -0.1700
Data Index: 2348644 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19