Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4678 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.8388. Min Act: -0.1700
Data Index: 5765972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.7450. Min Act: -0.1700
Data Index: 5295828 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.7450. Min Act: -0.1700
Data Index: 5600621 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.7137. Min Act: -0.1700
Data Index: 5998292 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6824. Min Act: -0.1700
Data Index: 4638529 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6824. Min Act: -0.1700
Data Index: 8051354 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6824. Min Act: -0.1700
Data Index: 3029993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6824. Min Act: -0.1700
Data Index: 3022567 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6824. Min Act: -0.1700
Data Index: 5355044 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6511. Min Act: -0.1700
Data Index: 2893863 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6511. Min Act: -0.1700
Data Index: 400158 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6511. Min Act: -0.1700
Data Index: 2877648 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6511. Min Act: -0.1700
Data Index: 6473963 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6511. Min Act: -0.1700
Data Index: 6526273 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6511. Min Act: -0.1700
Data Index: 5213627 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6511. Min Act: -0.1700
Data Index: 4441930 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6511. Min Act: -0.1700
Data Index: 5169519 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6198. Min Act: -0.1700
Data Index: 1793747 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6198. Min Act: -0.1700
Data Index: 953782 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8388. Min Range: -3.8388
Max Act: 3.6198. Min Act: -0.1700
Data Index: 4322034 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19