Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1404 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.5089. Min Act: -0.1700
Data Index: 684133 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.5714. Min Act: -0.1700
Data Index: 8482621 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.5089. Min Act: -0.1700
Data Index: 4059625 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.4464. Min Act: -0.1700
Data Index: 6261269 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.5089. Min Act: -0.1700
Data Index: 4912297 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.5089. Min Act: -0.1700
Data Index: 6495364 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.4464. Min Act: -0.1700
Data Index: 3104925 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.4464. Min Act: -0.1700
Data Index: 8448699 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.4464. Min Act: -0.1700
Data Index: 7706109 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.4464. Min Act: -0.1700
Data Index: 1886722 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.3839. Min Act: -0.1700
Data Index: 6591655 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.3839. Min Act: -0.1700
Data Index: 5205183 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.3526. Min Act: -0.1700
Data Index: 3220413 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.3526. Min Act: -0.1700
Data Index: 4596258 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.3839. Min Act: -0.1700
Data Index: 8674235 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.3526. Min Act: -0.1700
Data Index: 5858535 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.3214. Min Act: -0.1700
Data Index: 721621 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.2901. Min Act: -0.1700
Data Index: 4774414 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.3214. Min Act: -0.1700
Data Index: 8431930 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5714. Min Range: -7.5714
Max Act: 7.2901. Min Act: -0.1700
Data Index: 1653591 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19