Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2153 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0651. Min Range: -4.0651
Max Act: 4.0651. Min Act: -0.1700
Data Index: 5156100 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0651. Min Range: -4.0651
Max Act: 4.0025. Min Act: -0.1700
Data Index: 3597791 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0651. Min Range: -4.0651
Max Act: 4.0338. Min Act: -0.1700
Data Index: 4048417 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0651. Min Range: -4.0651
Max Act: 4.0025. Min Act: -0.1700
Data Index: 6855129 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0651. Min Range: -4.0651
Max Act: 4.0025. Min Act: -0.1700
Data Index: 3454154 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0651. Min Range: -4.0651
Max Act: 4.0025. Min Act: -0.1700
Data Index: 1529583 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0651. Min Range: -4.0651
Max Act: 4.0025. Min Act: -0.1700
Data Index: 4936370 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0651. Min Range: -4.0651
Max Act: 4.0025. Min Act: -0.1700
Data Index: 4733023 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9713. Min Act: -0.1700
Data Index: 2030518 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9400. Min Act: -0.1700
Data Index: 7973042 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9713. Min Act: -0.1700
Data Index: 1474306 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9400. Min Act: -0.1700
Data Index: 1746 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9088. Min Act: -0.1700
Data Index: 3630974 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9088. Min Act: -0.1700
Data Index: 7420810 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9088. Min Act: -0.1700
Data Index: 5625985 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9400. Min Act: -0.1700
Data Index: 4278492 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9088. Min Act: -0.1700
Data Index: 5785753 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9400. Min Act: -0.1700
Data Index: 3709891 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9088. Min Act: -0.1700
Data Index: 5283492 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0651. Min Range: -4.0651
Max Act: 3.9088. Min Act: -0.1700
Data Index: 117895 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19