Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.2605. Min Act: -0.1700
Data Index: 5311286 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1980. Min Act: -0.1700
Data Index: 5530816 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1667. Min Act: -0.1700
Data Index: 1988116 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1980. Min Act: -0.1700
Data Index: 7976079 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1667. Min Act: -0.1700
Data Index: 3384697 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1667. Min Act: -0.1700
Data Index: 2771029 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1667. Min Act: -0.1700
Data Index: 2818402 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1355. Min Act: -0.1700
Data Index: 6007825 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1355. Min Act: -0.1700
Data Index: 4432562 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1355. Min Act: -0.1700
Data Index: 2916851 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1355. Min Act: -0.1700
Data Index: 8757088 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1355. Min Act: -0.1700
Data Index: 7964665 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1355. Min Act: -0.1700
Data Index: 6271946 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1042. Min Act: -0.1700
Data Index: 4180873 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.0730. Min Act: -0.1700
Data Index: 4238222 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1042. Min Act: -0.1700
Data Index: 3233077 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1042. Min Act: -0.1700
Data Index: 4482811 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1042. Min Act: -0.1700
Data Index: 1637994 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1042. Min Act: -0.1700
Data Index: 4670639 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2605. Min Range: -5.2605
Max Act: 5.1042. Min Act: -0.1700
Data Index: 5321782 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19