Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4269 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0004. Min Range: -4.0004
Max Act: 4.0004. Min Act: -0.1700
Data Index: 4579930 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.6564. Min Act: -0.1700
Data Index: 4579928 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.6251. Min Act: -0.1700
Data Index: 4579929 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.5625. Min Act: -0.1700
Data Index: 2375987 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.3745. Min Act: -0.1700
Data Index: 2375996 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.3274. Min Act: -0.1700
Data Index: 2376002 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.3117. Min Act: -0.1700
Data Index: 2375998 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.2803. Min Act: -0.1700
Data Index: 2375988 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.2646. Min Act: -0.1700
Data Index: 4700112 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.2646. Min Act: -0.1700
Data Index: 891931 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.2018. Min Act: -0.1700
Data Index: 2375984 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.2018. Min Act: -0.1700
Data Index: 2375993 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.1860. Min Act: -0.1700
Data Index: 8479957 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.1703. Min Act: -0.1700
Data Index: 2375989 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.1860. Min Act: -0.1700
Data Index: 7726162 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.1860. Min Act: -0.1700
Data Index: 6290441 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.2018. Min Act: -0.1700
Data Index: 2375992 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.1703. Min Act: -0.1700
Data Index: 2311175 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.1703. Min Act: -0.1700
Data Index: 2375991 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0004. Min Range: -4.0004
Max Act: 3.1703. Min Act: -0.1700
Data Index: 208338 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19