Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1108 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4714. Min Range: -8.4714
Max Act: 8.4714. Min Act: -0.1700
Data Index: 7382805 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4714. Min Range: -8.4714
Max Act: 8.2214. Min Act: -0.1700
Data Index: 4272742 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4714. Min Range: -8.4714
Max Act: 8.1589. Min Act: -0.1700
Data Index: 4493579 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.9402. Min Act: -0.1700
Data Index: 7709058 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.9402. Min Act: -0.1700
Data Index: 2663194 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.7839. Min Act: -0.1700
Data Index: 8525502 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.5652. Min Act: -0.1700
Data Index: 509918 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.5652. Min Act: -0.1700
Data Index: 1383194 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.5027. Min Act: -0.1700
Data Index: 7382806 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.5339. Min Act: -0.1700
Data Index: 8268596 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4714. Min Act: -0.1700
Data Index: 4987810 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4714. Min Act: -0.1700
Data Index: 7195642 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4714. Min Act: -0.1700
Data Index: 7004538 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4402. Min Act: -0.1700
Data Index: 2155913 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4714. Min Act: -0.1700
Data Index: 828016 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4714. Min Act: -0.1700
Data Index: 8095672 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4714. Min Act: -0.1700
Data Index: 4663366 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4402. Min Act: -0.1700
Data Index: 2288165 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4402. Min Act: -0.1700
Data Index: 2668450 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4402. Min Act: -0.1700
Data Index: 3639532 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19