Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4068 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1648. Min Range: -6.1648
Max Act: 6.1648. Min Act: -0.1700
Data Index: 300437 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1648. Min Range: -6.1648
Max Act: 6.1023. Min Act: -0.1700
Data Index: 5506777 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.8523. Min Act: -0.1700
Data Index: 300435 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.6961. Min Act: -0.1700
Data Index: 6489562 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.6336. Min Act: -0.1700
Data Index: 4557048 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.6023. Min Act: -0.1700
Data Index: 7750029 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.5398. Min Act: -0.1700
Data Index: 7733081 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.5086. Min Act: -0.1700
Data Index: 3988311 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.4461. Min Act: -0.1700
Data Index: 4795995 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.4148. Min Act: -0.1700
Data Index: 3098478 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.4148. Min Act: -0.1700
Data Index: 3893413 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.4148. Min Act: -0.1700
Data Index: 3706595 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.4148. Min Act: -0.1700
Data Index: 3547084 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.3836. Min Act: -0.1700
Data Index: 750585 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.3523. Min Act: -0.1700
Data Index: 1567657 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.3211. Min Act: -0.1700
Data Index: 2352140 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.3211. Min Act: -0.1700
Data Index: 2860194 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.3211. Min Act: -0.1700
Data Index: 1482533 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.3211. Min Act: -0.1700
Data Index: 10634 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1648. Min Range: -6.1648
Max Act: 5.2898. Min Act: -0.1700
Data Index: 543652 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19