Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.9599. Min Act: -0.1700
Data Index: 7062901 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.9287. Min Act: -0.1700
Data Index: 5864171 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.9287. Min Act: -0.1700
Data Index: 7906394 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.8037. Min Act: -0.1700
Data Index: 6493533 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.7724. Min Act: -0.1700
Data Index: 113534 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.8037. Min Act: -0.1700
Data Index: 2079832 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.7412. Min Act: -0.1700
Data Index: 2593367 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.6787. Min Act: -0.1700
Data Index: 4599388 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.7412. Min Act: -0.1700
Data Index: 4218823 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.7099. Min Act: -0.1700
Data Index: 4368006 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.6474. Min Act: -0.1700
Data Index: 7810487 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.6787. Min Act: -0.1700
Data Index: 5148284 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.7099. Min Act: -0.1700
Data Index: 5395202 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.6787. Min Act: -0.1700
Data Index: 8314526 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.6162. Min Act: -0.1700
Data Index: 7953587 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.6474. Min Act: -0.1700
Data Index: 8086628 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.6474. Min Act: -0.1700
Data Index: 7144883 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.5849. Min Act: -0.1700
Data Index: 2473245 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.6162. Min Act: -0.1700
Data Index: 7721394 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9599. Min Range: -4.9599
Max Act: 4.5537. Min Act: -0.1700
Data Index: 2279038 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19