Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4979 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0990. Min Range: -10.0990
Max Act: 10.0990. Min Act: -0.1700
Data Index: 7053203 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0990. Min Range: -10.0990
Max Act: 9.2240. Min Act: -0.1700
Data Index: 7065652 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0990. Min Range: -10.0990
Max Act: 9.0365. Min Act: -0.1700
Data Index: 6614306 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0990. Min Range: -10.0990
Max Act: 9.0365. Min Act: -0.1700
Data Index: 8470380 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.9115. Min Act: -0.1700
Data Index: 631584 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.8490. Min Act: -0.1700
Data Index: 571162 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.8490. Min Act: -0.1700
Data Index: 7127209 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.7865. Min Act: -0.1700
Data Index: 8290931 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.7240. Min Act: -0.1700
Data Index: 4599146 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.7865. Min Act: -0.1700
Data Index: 7541376 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.6615. Min Act: -0.1700
Data Index: 4818141 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.6615. Min Act: -0.1700
Data Index: 2410906 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.6615. Min Act: -0.1700
Data Index: 4814091 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.6615. Min Act: -0.1700
Data Index: 4560519 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.5365. Min Act: -0.1700
Data Index: 6287565 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.5365. Min Act: -0.1700
Data Index: 7816589 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.5365. Min Act: -0.1700
Data Index: 5603841 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.4740. Min Act: -0.1700
Data Index: 2428357 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.4740. Min Act: -0.1700
Data Index: 5341458 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0990. Min Range: -10.0990
Max Act: 8.4740. Min Act: -0.1700
Data Index: 2835901 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19