Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1667. Min Act: -0.1700
Data Index: 2419510 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1355. Min Act: -0.1700
Data Index: 5396954 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1042. Min Act: -0.1700
Data Index: 8001643 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1042. Min Act: -0.1700
Data Index: 4568582 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1042. Min Act: -0.1700
Data Index: 2345814 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1042. Min Act: -0.1700
Data Index: 7707336 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1042. Min Act: -0.1700
Data Index: 3339556 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1042. Min Act: -0.1700
Data Index: 7061387 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1042. Min Act: -0.1700
Data Index: 6728224 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1042. Min Act: -0.1700
Data Index: 6650557 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.0730. Min Act: -0.1700
Data Index: 4309340 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1042. Min Act: -0.1700
Data Index: 2728670 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.0730. Min Act: -0.1700
Data Index: 152153 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.0730. Min Act: -0.1700
Data Index: 4485669 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.1042. Min Act: -0.1700
Data Index: 5433110 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.0730. Min Act: -0.1700
Data Index: 2521361 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.0417. Min Act: -0.1700
Data Index: 2475728 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.0417. Min Act: -0.1700
Data Index: 2519702 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.0417. Min Act: -0.1700
Data Index: 4741600 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1667. Min Range: -4.1667
Max Act: 4.0417. Min Act: -0.1700
Data Index: 4957937 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19