Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3177 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3069. Min Range: -10.3069
Max Act: 10.3069. Min Act: -0.1700
Data Index: 3351305 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3069. Min Range: -10.3069
Max Act: 10.1819. Min Act: -0.1700
Data Index: 7803163 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3069. Min Range: -10.3069
Max Act: 10.0569. Min Act: -0.1700
Data Index: 4879990 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.9944. Min Act: -0.1700
Data Index: 1081127 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.9944. Min Act: -0.1700
Data Index: 7125317 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.9319. Min Act: -0.1700
Data Index: 3978466 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.9319. Min Act: -0.1700
Data Index: 546556 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.9319. Min Act: -0.1700
Data Index: 5680265 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.9319. Min Act: -0.1700
Data Index: 217579 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.8694. Min Act: -0.1700
Data Index: 5897600 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.8694. Min Act: -0.1700
Data Index: 8398163 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.8694. Min Act: -0.1700
Data Index: 6915311 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.8069. Min Act: -0.1700
Data Index: 1353322 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.8069. Min Act: -0.1700
Data Index: 1866872 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.8069. Min Act: -0.1700
Data Index: 8778317 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.8069. Min Act: -0.1700
Data Index: 7085885 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.8069. Min Act: -0.1700
Data Index: 5930727 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.7444. Min Act: -0.1700
Data Index: 2338764 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.7444. Min Act: -0.1700
Data Index: 6768788 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3069. Min Range: -10.3069
Max Act: 9.6819. Min Act: -0.1700
Data Index: 3889618 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19