Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3777 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0712. Min Range: -5.0712
Max Act: 5.0712. Min Act: -0.1700
Data Index: 6371132 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0712. Min Range: -5.0712
Max Act: 5.0399. Min Act: -0.1700
Data Index: 8233396 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.8837. Min Act: -0.1700
Data Index: 7568874 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.8212. Min Act: -0.1700
Data Index: 867885 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.8524. Min Act: -0.1700
Data Index: 1667406 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.8837. Min Act: -0.1700
Data Index: 2415644 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.7587. Min Act: -0.1700
Data Index: 1530329 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.7587. Min Act: -0.1700
Data Index: 2945828 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.7587. Min Act: -0.1700
Data Index: 4762367 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.7274. Min Act: -0.1700
Data Index: 1719127 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.7274. Min Act: -0.1700
Data Index: 2299435 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.7274. Min Act: -0.1700
Data Index: 5929909 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.6649. Min Act: -0.1700
Data Index: 5638799 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.6649. Min Act: -0.1700
Data Index: 8520935 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.6337. Min Act: -0.1700
Data Index: 73018 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.6024. Min Act: -0.1700
Data Index: 7303142 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.6649. Min Act: -0.1700
Data Index: 75246 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.6649. Min Act: -0.1700
Data Index: 5800084 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.6337. Min Act: -0.1700
Data Index: 5037322 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0712. Min Range: -5.0712
Max Act: 4.6649. Min Act: -0.1700
Data Index: 6747433 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19