Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4590 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3610. Min Range: -5.3610
Max Act: 5.3610. Min Act: -0.1700
Data Index: 5086526 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3610. Min Range: -5.3610
Max Act: 5.3297. Min Act: -0.1700
Data Index: 3146644 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3610. Min Range: -5.3610
Max Act: 5.2360. Min Act: -0.1700
Data Index: 1601386 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3610. Min Range: -5.3610
Max Act: 5.2047. Min Act: -0.1700
Data Index: 5037655 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3610. Min Range: -5.3610
Max Act: 5.1422. Min Act: -0.1700
Data Index: 2336703 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3610. Min Range: -5.3610
Max Act: 5.1110. Min Act: -0.1700
Data Index: 1265598 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3610. Min Range: -5.3610
Max Act: 5.1110. Min Act: -0.1700
Data Index: 6401603 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3610. Min Range: -5.3610
Max Act: 5.0797. Min Act: -0.1700
Data Index: 1129351 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3610. Min Range: -5.3610
Max Act: 5.0485. Min Act: -0.1700
Data Index: 2159433 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3610. Min Range: -5.3610
Max Act: 5.0172. Min Act: -0.1700
Data Index: 1248372 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3610. Min Range: -5.3610
Max Act: 4.9234. Min Act: -0.1700
Data Index: 1793780 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3610. Min Range: -5.3610
Max Act: 4.9547. Min Act: -0.1700
Data Index: 1322589 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3610. Min Range: -5.3610
Max Act: 4.9547. Min Act: -0.1700
Data Index: 5868488 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3610. Min Range: -5.3610
Max Act: 4.9234. Min Act: -0.1700
Data Index: 4075357 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3610. Min Range: -5.3610
Max Act: 4.9234. Min Act: -0.1700
Data Index: 5303700 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3610. Min Range: -5.3610
Max Act: 4.9234. Min Act: -0.1700
Data Index: 8317542 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3610. Min Range: -5.3610
Max Act: 4.8922. Min Act: -0.1700
Data Index: 5531543 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3610. Min Range: -5.3610
Max Act: 4.8922. Min Act: -0.1700
Data Index: 8222919 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3610. Min Range: -5.3610
Max Act: 4.8609. Min Act: -0.1700
Data Index: 6547137 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3610. Min Range: -5.3610
Max Act: 4.8297. Min Act: -0.1700
Data Index: 1605559 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19