Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2438 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.9360. Min Act: -0.1700
Data Index: 6313966 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.9047. Min Act: -0.1700
Data Index: 5004389 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.8735. Min Act: -0.1700
Data Index: 5359393 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.8422. Min Act: -0.1700
Data Index: 7248670 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.7797. Min Act: -0.1700
Data Index: 1640981 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.7485. Min Act: -0.1700
Data Index: 2554475 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.7485. Min Act: -0.1700
Data Index: 2587754 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.6860. Min Act: -0.1700
Data Index: 8732087 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.6860. Min Act: -0.1700
Data Index: 2664074 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.6860. Min Act: -0.1700
Data Index: 4280992 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.6860. Min Act: -0.1700
Data Index: 4219107 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.6547. Min Act: -0.1700
Data Index: 758435 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.6235. Min Act: -0.1700
Data Index: 5461284 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.5922. Min Act: -0.1700
Data Index: 1864061 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.6235. Min Act: -0.1700
Data Index: 1192262 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.6235. Min Act: -0.1700
Data Index: 6950435 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.5610. Min Act: -0.1700
Data Index: 15986 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.5610. Min Act: -0.1700
Data Index: 8776960 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.5297. Min Act: -0.1700
Data Index: 202059 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9360. Min Range: -5.9360
Max Act: 5.5610. Min Act: -0.1700
Data Index: 6700465 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19