Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4266 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.9723. Min Act: -0.1700
Data Index: 3082216 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8530. Min Act: -0.1699
Data Index: 5241743 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8701. Min Act: -0.1700
Data Index: 2033223 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8530. Min Act: -0.1700
Data Index: 8631865 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.6632. Min Act: -0.1700
Data Index: 8777731 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.6283. Min Act: -0.1700
Data Index: 3883658 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.6109. Min Act: -0.1696
Data Index: 5202868 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5934. Min Act: -0.1689
Data Index: 8596602 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5934. Min Act: -0.1697
Data Index: 554019 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5759. Min Act: -0.1696
Data Index: 1568156 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5759. Min Act: -0.1699
Data Index: 2175397 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5759. Min Act: -0.1699
Data Index: 1169863 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5759. Min Act: -0.1700
Data Index: 812409 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5585. Min Act: -0.1686
Data Index: 2919388 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5409. Min Act: -0.1699
Data Index: 1443326 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5409. Min Act: -0.1700
Data Index: 299147 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5234. Min Act: -0.1675
Data Index: 2257634 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5234. Min Act: -0.1693
Data Index: 7942856 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5409. Min Act: -0.1700
Data Index: 2166723 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.5409. Min Act: -0.1699
Data Index: 3103635 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19