Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5644 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.4407. Min Act: -0.1700
Data Index: 7062891 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.4407. Min Act: -0.1700
Data Index: 5440734 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.3782. Min Act: -0.1700
Data Index: 2301822 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.3157. Min Act: -0.1700
Data Index: 2718605 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.2532. Min Act: -0.1700
Data Index: 1858317 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.2844. Min Act: -0.1700
Data Index: 6784710 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.2219. Min Act: -0.1700
Data Index: 1773520 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.1907. Min Act: -0.1700
Data Index: 6524114 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.1907. Min Act: -0.1700
Data Index: 253592 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.1907. Min Act: -0.1700
Data Index: 6232443 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.1594. Min Act: -0.1700
Data Index: 6142123 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.1594. Min Act: -0.1700
Data Index: 1873941 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.1594. Min Act: -0.1700
Data Index: 8283121 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.1594. Min Act: -0.1700
Data Index: 589521 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.1282. Min Act: -0.1700
Data Index: 8062378 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.1282. Min Act: -0.1700
Data Index: 5524110 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.0969. Min Act: -0.1700
Data Index: 697198 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.0657. Min Act: -0.1700
Data Index: 3908596 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.0969. Min Act: -0.1700
Data Index: 1893396 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4407. Min Range: -6.4407
Max Act: 6.1282. Min Act: -0.1700
Data Index: 7150761 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19