Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2746 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.4236. Min Act: -0.1700
Data Index: 4936625 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.1736. Min Act: -0.1700
Data Index: 7297145 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.1111. Min Act: -0.1700
Data Index: 3976830 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.1111. Min Act: -0.1700
Data Index: 1057292 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.1111. Min Act: -0.1700
Data Index: 1724689 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.0173. Min Act: -0.1700
Data Index: 3019331 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.0486. Min Act: -0.1700
Data Index: 4264566 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.9861. Min Act: -0.1700
Data Index: 1036837 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.9236. Min Act: -0.1700
Data Index: 5148635 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.9548. Min Act: -0.1700
Data Index: 6667476 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.8923. Min Act: -0.1700
Data Index: 1462065 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.9236. Min Act: -0.1700
Data Index: 3753358 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.8923. Min Act: -0.1700
Data Index: 2839837 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.9236. Min Act: -0.1700
Data Index: 2848569 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.9236. Min Act: -0.1700
Data Index: 8148438 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.8611. Min Act: -0.1700
Data Index: 3067593 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.8923. Min Act: -0.1700
Data Index: 2731640 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.8611. Min Act: -0.1700
Data Index: 2627741 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.8611. Min Act: -0.1700
Data Index: 7846638 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4236. Min Range: -6.4236
Max Act: 5.8611. Min Act: -0.1700
Data Index: 429476 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19