Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2460. Min Range: -6.2460
Max Act: 6.2460. Min Act: -0.1700
Data Index: 3290764 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2460. Min Range: -6.2460
Max Act: 6.1210. Min Act: -0.1700
Data Index: 3230347 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2460. Min Range: -6.2460
Max Act: 6.0585. Min Act: -0.1700
Data Index: 5562689 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2460. Min Range: -6.2460
Max Act: 6.0585. Min Act: -0.1700
Data Index: 3314517 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2460. Min Range: -6.2460
Max Act: 6.0273. Min Act: -0.1700
Data Index: 5534063 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2460. Min Range: -6.2460
Max Act: 6.0273. Min Act: -0.1700
Data Index: 7523841 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.9960. Min Act: -0.1700
Data Index: 2067107 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.9960. Min Act: -0.1700
Data Index: 2639902 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.9648. Min Act: -0.1700
Data Index: 2181865 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.9335. Min Act: -0.1700
Data Index: 8631958 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.9335. Min Act: -0.1700
Data Index: 8117881 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.9023. Min Act: -0.1700
Data Index: 3324462 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.8710. Min Act: -0.1700
Data Index: 3162313 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.9023. Min Act: -0.1700
Data Index: 3115564 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.8398. Min Act: -0.1700
Data Index: 6258988 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.8710. Min Act: -0.1700
Data Index: 1017799 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.8398. Min Act: -0.1700
Data Index: 6672789 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.8398. Min Act: -0.1700
Data Index: 3320223 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.8398. Min Act: -0.1700
Data Index: 3193414 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2460. Min Range: -6.2460
Max Act: 5.8398. Min Act: -0.1700
Data Index: 7761687 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19