Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 925 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.8106. Min Act: -0.1700
Data Index: 6547370 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.8106. Min Act: -0.1700
Data Index: 8475854 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.7481. Min Act: -0.1700
Data Index: 3839010 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.7481. Min Act: -0.1700
Data Index: 1514079 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.7481. Min Act: -0.1694
Data Index: 1965326 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.7481. Min Act: -0.1700
Data Index: 5458272 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.7481. Min Act: -0.1700
Data Index: 8680226 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6543. Min Act: -0.1700
Data Index: 5792992 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6856. Min Act: -0.1700
Data Index: 1342909 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6856. Min Act: -0.1700
Data Index: 6030138 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6856. Min Act: -0.1700
Data Index: 170939 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6856. Min Act: -0.1700
Data Index: 5148836 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6856. Min Act: -0.1700
Data Index: 2934739 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6856. Min Act: -0.1700
Data Index: 708391 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6543. Min Act: -0.1700
Data Index: 507496 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6856. Min Act: -0.1700
Data Index: 6241279 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6543. Min Act: -0.1700
Data Index: 5838408 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6231. Min Act: -0.1700
Data Index: 2449274 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6543. Min Act: -0.1700
Data Index: 2979445 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6543. Min Act: -0.1700
Data Index: 6135017 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19