Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3380 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1004. Min Range: -6.1004
Max Act: 6.1004. Min Act: -0.1700
Data Index: 253590 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1004. Min Range: -6.1004
Max Act: 6.0691. Min Act: -0.1700
Data Index: 4463012 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1004. Min Range: -6.1004
Max Act: 6.0691. Min Act: -0.1700
Data Index: 4559802 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1004. Min Range: -6.1004
Max Act: 6.0379. Min Act: -0.1700
Data Index: 5006835 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1004. Min Range: -6.1004
Max Act: 6.0066. Min Act: -0.1700
Data Index: 7537249 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1004. Min Range: -6.1004
Max Act: 6.0066. Min Act: -0.1700
Data Index: 7921190 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9754. Min Act: -0.1700
Data Index: 4219486 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 1909669 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 1864907 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 1049984 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 1596953 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 3659493 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 2274321 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 1475626 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 3357405 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 3217085 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 669387 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 3215093 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 3403902 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1004. Min Range: -6.1004
Max Act: 5.9441. Min Act: -0.1700
Data Index: 247856 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19