Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1375 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.3678. Min Act: -0.1700
Data Index: 4683738 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.3365. Min Act: -0.1700
Data Index: 6264916 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.1803. Min Act: -0.1700
Data Index: 6263983 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.1178. Min Act: -0.1700
Data Index: 1542194 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.1178. Min Act: -0.1700
Data Index: 1384049 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.1178. Min Act: -0.1700
Data Index: 6941105 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.0865. Min Act: -0.1700
Data Index: 6011489 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.0865. Min Act: -0.1700
Data Index: 4977741 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.0240. Min Act: -0.1700
Data Index: 3624306 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.0553. Min Act: -0.1700
Data Index: 3306018 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.0553. Min Act: -0.1700
Data Index: 731824 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.0240. Min Act: -0.1700
Data Index: 1835172 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3678. Min Range: -4.3678
Max Act: 4.0240. Min Act: -0.1700
Data Index: 6267544 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3678. Min Range: -4.3678
Max Act: 3.9927. Min Act: -0.1700
Data Index: 2599215 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3678. Min Range: -4.3678
Max Act: 3.9927. Min Act: -0.1700
Data Index: 6717707 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3678. Min Range: -4.3678
Max Act: 3.9927. Min Act: -0.1700
Data Index: 5116011 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3678. Min Range: -4.3678
Max Act: 3.9615. Min Act: -0.1700
Data Index: 5477674 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3678. Min Range: -4.3678
Max Act: 3.9615. Min Act: -0.1700
Data Index: 5079498 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3678. Min Range: -4.3678
Max Act: 3.9615. Min Act: -0.1700
Data Index: 4621846 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3678. Min Range: -4.3678
Max Act: 3.9615. Min Act: -0.1700
Data Index: 591025 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19