Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.7264. Min Act: -0.1700
Data Index: 6648630 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.6014. Min Act: -0.1700
Data Index: 1985487 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.6014. Min Act: -0.1700
Data Index: 7908545 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.4764. Min Act: -0.1700
Data Index: 2373109 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.4139. Min Act: -0.1700
Data Index: 1385449 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.4764. Min Act: -0.1700
Data Index: 5510186 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.4764. Min Act: -0.1700
Data Index: 3519856 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.4139. Min Act: -0.1700
Data Index: 4191567 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.4139. Min Act: -0.1700
Data Index: 672751 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.4139. Min Act: -0.1700
Data Index: 8453803 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.4139. Min Act: -0.1700
Data Index: 4807912 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.4139. Min Act: -0.1700
Data Index: 2234427 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.4139. Min Act: -0.1699
Data Index: 6833339 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.3514. Min Act: -0.1700
Data Index: 2251844 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.3514. Min Act: -0.1700
Data Index: 3367939 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.3514. Min Act: -0.1700
Data Index: 3111416 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.3514. Min Act: -0.1700
Data Index: 1371708 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.2889. Min Act: -0.1700
Data Index: 1497494 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.2889. Min Act: -0.1700
Data Index: 5687061 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7264. Min Range: -8.7264
Max Act: 8.2889. Min Act: -0.1700
Data Index: 282559 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19