Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4587 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.9365. Min Act: -0.1700
Data Index: 1892206 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.6865. Min Act: -0.1700
Data Index: 7622611 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.5615. Min Act: -0.1700
Data Index: 605399 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.4365. Min Act: -0.1700
Data Index: 6956016 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.4990. Min Act: -0.1700
Data Index: 7493897 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.3115. Min Act: -0.1700
Data Index: 812308 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.3115. Min Act: -0.1700
Data Index: 4356570 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.3115. Min Act: -0.1700
Data Index: 7757021 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.2490. Min Act: -0.1700
Data Index: 8823062 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.3115. Min Act: -0.1700
Data Index: 8773296 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.3115. Min Act: -0.1700
Data Index: 5538231 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.3115. Min Act: -0.1700
Data Index: 4170751 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.2490. Min Act: -0.1700
Data Index: 6728209 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.2490. Min Act: -0.1700
Data Index: 7648519 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.3115. Min Act: -0.1700
Data Index: 7173576 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.2490. Min Act: -0.1700
Data Index: 109575 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.1865. Min Act: -0.1700
Data Index: 7782249 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.1865. Min Act: -0.1700
Data Index: 989102 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.1240. Min Act: -0.1700
Data Index: 4345593 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9365. Min Range: -8.9365
Max Act: 8.0615. Min Act: -0.1700
Data Index: 86170 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19