Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3985 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0795. Min Range: -2.0795
Max Act: 2.0795. Min Act: -0.1700
Data Index: 561420 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0795. Min Range: -2.0795
Max Act: 2.0290. Min Act: -0.1700
Data Index: 1562436 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0795. Min Range: -2.0795
Max Act: 2.0290. Min Act: -0.1700
Data Index: 4843407 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9953. Min Act: -0.1700
Data Index: 1323817 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9783. Min Act: -0.1700
Data Index: 3396275 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9783. Min Act: -0.1700
Data Index: 3428898 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9783. Min Act: -0.1700
Data Index: 1655620 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9783. Min Act: -0.1700
Data Index: 4797503 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9783. Min Act: -0.1700
Data Index: 4596555 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9783. Min Act: -0.1700
Data Index: 4000264 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9783. Min Act: -0.1700
Data Index: 4252994 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9783. Min Act: -0.1700
Data Index: 7063354 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9614. Min Act: -0.1700
Data Index: 8040847 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9274. Min Act: -0.1700
Data Index: 2152290 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9444. Min Act: -0.1700
Data Index: 4789354 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9444. Min Act: -0.1700
Data Index: 5262114 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9444. Min Act: -0.1700
Data Index: 2465380 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9614. Min Act: -0.1700
Data Index: 5520627 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9614. Min Act: -0.1700
Data Index: 2946078 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0795. Min Range: -2.0795
Max Act: 1.9444. Min Act: -0.1700
Data Index: 185767 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19