Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4417 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4273. Min Range: -7.4273
Max Act: 7.4273. Min Act: -0.1700
Data Index: 7325771 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4273. Min Range: -7.4273
Max Act: 7.3648. Min Act: -0.1700
Data Index: 51930 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4273. Min Range: -7.4273
Max Act: 7.1773. Min Act: -0.1700
Data Index: 5272154 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4273. Min Range: -7.4273
Max Act: 7.1148. Min Act: -0.1700
Data Index: 3488695 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4273. Min Range: -7.4273
Max Act: 7.0523. Min Act: -0.1700
Data Index: 85199 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4273. Min Range: -7.4273
Max Act: 7.0836. Min Act: -0.1700
Data Index: 5716291 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4273. Min Range: -7.4273
Max Act: 7.0211. Min Act: -0.1700
Data Index: 7761049 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4273. Min Range: -7.4273
Max Act: 7.0211. Min Act: -0.1700
Data Index: 7148180 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.9898. Min Act: -0.1700
Data Index: 4881295 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.9586. Min Act: -0.1700
Data Index: 7784009 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.8961. Min Act: -0.1700
Data Index: 3555257 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.8648. Min Act: -0.1700
Data Index: 7501558 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.8648. Min Act: -0.1700
Data Index: 2795389 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.8648. Min Act: -0.1700
Data Index: 866832 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.8336. Min Act: -0.1700
Data Index: 1784345 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.8023. Min Act: -0.1700
Data Index: 786890 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.7711. Min Act: -0.1700
Data Index: 3059842 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.7711. Min Act: -0.1700
Data Index: 3444064 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.7711. Min Act: -0.1700
Data Index: 626585 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4273. Min Range: -7.4273
Max Act: 6.7711. Min Act: -0.1700
Data Index: 2845012 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19