Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4891 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.8677. Min Act: -0.1700
Data Index: 2762775 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.8677. Min Act: -0.1700
Data Index: 7021417 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.8677. Min Act: -0.1700
Data Index: 6344846 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.8052. Min Act: -0.1700
Data Index: 4260873 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.7427. Min Act: -0.1700
Data Index: 5319008 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.7427. Min Act: -0.1700
Data Index: 5344850 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.6802. Min Act: -0.1700
Data Index: 7711411 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.6489. Min Act: -0.1700
Data Index: 411168 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.6177. Min Act: -0.1700
Data Index: 5408112 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.6177. Min Act: -0.1700
Data Index: 3473240 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.5552. Min Act: -0.1700
Data Index: 1963930 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.5239. Min Act: -0.1700
Data Index: 4442603 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.4927. Min Act: -0.1700
Data Index: 159903 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.4927. Min Act: -0.1700
Data Index: 8518303 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.4927. Min Act: -0.1700
Data Index: 5840503 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.4302. Min Act: -0.1700
Data Index: 112746 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.3677. Min Act: -0.1700
Data Index: 7664134 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.3677. Min Act: -0.1700
Data Index: 4755852 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.3052. Min Act: -0.1700
Data Index: 5374645 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8677. Min Range: -7.8677
Max Act: 7.3364. Min Act: -0.1700
Data Index: 8222906 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19