Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2439 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0833. Min Range: -5.0833
Max Act: 5.0833. Min Act: -0.1700
Data Index: 6932641 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0833. Min Range: -5.0833
Max Act: 5.0208. Min Act: -0.1700
Data Index: 5603986 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0833. Min Range: -5.0833
Max Act: 5.0521. Min Act: -0.1700
Data Index: 3398072 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0833. Min Range: -5.0833
Max Act: 5.0521. Min Act: -0.1700
Data Index: 8128477 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.9896. Min Act: -0.1700
Data Index: 1231897 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.9271. Min Act: -0.1700
Data Index: 6039199 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.9583. Min Act: -0.1700
Data Index: 8439010 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8646. Min Act: -0.1700
Data Index: 5875318 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8958. Min Act: -0.1700
Data Index: 5210076 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8958. Min Act: -0.1700
Data Index: 5643633 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8333. Min Act: -0.1700
Data Index: 3202152 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8958. Min Act: -0.1700
Data Index: 6405997 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8646. Min Act: -0.1700
Data Index: 7418389 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8646. Min Act: -0.1700
Data Index: 291819 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8333. Min Act: -0.1700
Data Index: 6434246 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8333. Min Act: -0.1700
Data Index: 4223530 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8646. Min Act: -0.1700
Data Index: 8505906 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8333. Min Act: -0.1700
Data Index: 3356646 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.8646. Min Act: -0.1700
Data Index: 1947730 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0833. Min Range: -5.0833
Max Act: 4.7708. Min Act: -0.1700
Data Index: 1014557 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19