Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1763 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5414. Min Range: -6.5414
Max Act: 6.5414. Min Act: -0.1700
Data Index: 4775252 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5414. Min Range: -6.5414
Max Act: 6.3539. Min Act: -0.1700
Data Index: 5320895 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5414. Min Range: -6.5414
Max Act: 6.2914. Min Act: -0.1700
Data Index: 6162524 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5414. Min Range: -6.5414
Max Act: 6.2289. Min Act: -0.1700
Data Index: 3746327 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5414. Min Range: -6.5414
Max Act: 6.2602. Min Act: -0.1700
Data Index: 6936558 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5414. Min Range: -6.5414
Max Act: 6.1977. Min Act: -0.1700
Data Index: 2792873 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5414. Min Range: -6.5414
Max Act: 6.1664. Min Act: -0.1700
Data Index: 3074539 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5414. Min Range: -6.5414
Max Act: 6.1664. Min Act: -0.1700
Data Index: 7051448 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5414. Min Range: -6.5414
Max Act: 6.0102. Min Act: -0.1700
Data Index: 4282789 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5414. Min Range: -6.5414
Max Act: 6.0414. Min Act: -0.1700
Data Index: 6228539 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5414. Min Range: -6.5414
Max Act: 5.9477. Min Act: -0.1700
Data Index: 2425840 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5414. Min Range: -6.5414
Max Act: 5.9789. Min Act: -0.1700
Data Index: 3280016 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5414. Min Range: -6.5414
Max Act: 5.9789. Min Act: -0.1700
Data Index: 3890128 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5414. Min Range: -6.5414
Max Act: 5.9477. Min Act: -0.1700
Data Index: 7312076 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5414. Min Range: -6.5414
Max Act: 5.9789. Min Act: -0.1700
Data Index: 1855572 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5414. Min Range: -6.5414
Max Act: 6.0102. Min Act: -0.1700
Data Index: 2614684 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5414. Min Range: -6.5414
Max Act: 5.9789. Min Act: -0.1700
Data Index: 7301663 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5414. Min Range: -6.5414
Max Act: 5.9477. Min Act: -0.1700
Data Index: 1175750 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5414. Min Range: -6.5414
Max Act: 5.9164. Min Act: -0.1700
Data Index: 1021308 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5414. Min Range: -6.5414
Max Act: 5.9164. Min Act: -0.1700
Data Index: 5526381 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19