Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4835 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.9604. Min Act: -0.1700
Data Index: 3099670 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.9604. Min Act: -0.1700
Data Index: 1477615 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.9435. Min Act: -0.1700
Data Index: 264413 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.9009. Min Act: -0.1689
Data Index: 1477608 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8753. Min Act: -0.1700
Data Index: 6140847 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8582. Min Act: -0.1700
Data Index: 383862 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8067. Min Act: -0.1700
Data Index: 4479104 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8153. Min Act: -0.1700
Data Index: 7012180 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7981. Min Act: -0.1700
Data Index: 4479116 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8067. Min Act: -0.1700
Data Index: 929165 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7895. Min Act: -0.1700
Data Index: 1477604 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7809. Min Act: -0.1676
Data Index: 1477585 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7809. Min Act: -0.1699
Data Index: 1477623 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7723. Min Act: -0.1689
Data Index: 2787139 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7723. Min Act: -0.1700
Data Index: 929166 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7809. Min Act: -0.1700
Data Index: 4479097 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7723. Min Act: -0.1699
Data Index: 5679730 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7809. Min Act: -0.1700
Data Index: 6140838 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7637. Min Act: -0.1700
Data Index: 1753766 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7637. Min Act: -0.1700
Data Index: 4197237 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19