Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2493 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.4444. Min Act: -0.1700
Data Index: 3472649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.4130. Min Act: -0.1700
Data Index: 2566054 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3660. Min Act: -0.1700
Data Index: 8430096 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3660. Min Act: -0.1700
Data Index: 4467439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3660. Min Act: -0.1700
Data Index: 3968784 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3346. Min Act: -0.1700
Data Index: 4081150 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3346. Min Act: -0.1700
Data Index: 3453903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3346. Min Act: -0.1700
Data Index: 7735035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3189. Min Act: -0.1700
Data Index: 2072505 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3189. Min Act: -0.1700
Data Index: 8023787 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3189. Min Act: -0.1700
Data Index: 5651585 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3032. Min Act: -0.1700
Data Index: 4007239 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.2875. Min Act: -0.1700
Data Index: 7914658 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3032. Min Act: -0.1700
Data Index: 3418631 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.3032. Min Act: -0.1700
Data Index: 6015654 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.2875. Min Act: -0.1700
Data Index: 87665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.2718. Min Act: -0.1700
Data Index: 5901436 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.2718. Min Act: -0.1700
Data Index: 6496644 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.2718. Min Act: -0.1700
Data Index: 5498059 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4444. Min Range: -3.4444
Max Act: 3.2718. Min Act: -0.1700
Data Index: 3827438 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19