Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 755 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.7437. Min Act: -0.1700
Data Index: 2305075 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.6187. Min Act: -0.1700
Data Index: 6230876 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.5875. Min Act: -0.1700
Data Index: 7155467 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.5562. Min Act: -0.1700
Data Index: 6511571 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.4937. Min Act: -0.1700
Data Index: 6881463 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.4937. Min Act: -0.1700
Data Index: 6565881 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.4625. Min Act: -0.1700
Data Index: 1068849 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.4625. Min Act: -0.1700
Data Index: 336159 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.4625. Min Act: -0.1700
Data Index: 2606970 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.4625. Min Act: -0.1700
Data Index: 3778950 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.4000. Min Act: -0.1700
Data Index: 3932349 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.4312. Min Act: -0.1700
Data Index: 7855207 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.4000. Min Act: -0.1700
Data Index: 3606101 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.3687. Min Act: -0.1700
Data Index: 251750 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.3375. Min Act: -0.1700
Data Index: 343197 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.3062. Min Act: -0.1700
Data Index: 4299106 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.3375. Min Act: -0.1700
Data Index: 3948660 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.3375. Min Act: -0.1700
Data Index: 3284200 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.3375. Min Act: -0.1700
Data Index: 7719021 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7437. Min Range: -5.7437
Max Act: 5.3375. Min Act: -0.1700
Data Index: 5378352 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19