Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6230 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2004. Min Range: -3.2004
Max Act: 3.2004. Min Act: -0.1700
Data Index: 5917694 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2004. Min Range: -3.2004
Max Act: 3.1375. Min Act: -0.1700
Data Index: 8606168 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2004. Min Range: -3.2004
Max Act: 3.1218. Min Act: -0.1700
Data Index: 7910838 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2004. Min Range: -3.2004
Max Act: 3.0745. Min Act: -0.1700
Data Index: 4900127 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2004. Min Range: -3.2004
Max Act: 3.0429. Min Act: -0.1700
Data Index: 1779556 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2004. Min Range: -3.2004
Max Act: 3.0113. Min Act: -0.1700
Data Index: 8552124 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9797. Min Act: -0.1700
Data Index: 7547024 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9955. Min Act: -0.1700
Data Index: 5292154 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9797. Min Act: -0.1700
Data Index: 4630554 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9797. Min Act: -0.1700
Data Index: 2998412 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9639. Min Act: -0.1700
Data Index: 3571261 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9797. Min Act: -0.1700
Data Index: 1970414 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9639. Min Act: -0.1700
Data Index: 4505686 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9639. Min Act: -0.1700
Data Index: 6128985 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9639. Min Act: -0.1700
Data Index: 1444342 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9639. Min Act: -0.1700
Data Index: 6939079 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9639. Min Act: -0.1700
Data Index: 6700973 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9639. Min Act: -0.1700
Data Index: 801795 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9481. Min Act: -0.1700
Data Index: 3687618 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2004. Min Range: -3.2004
Max Act: 2.9481. Min Act: -0.1700
Data Index: 6480392 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19