Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 820 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2520. Min Range: -5.2520
Max Act: 5.2520. Min Act: -0.1700
Data Index: 6375999 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2520. Min Range: -5.2520
Max Act: 5.0333. Min Act: -0.1700
Data Index: 460730 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2520. Min Range: -5.2520
Max Act: 5.0020. Min Act: -0.1700
Data Index: 4078952 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.9708. Min Act: -0.1700
Data Index: 2398441 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.9395. Min Act: -0.1700
Data Index: 6871610 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.8770. Min Act: -0.1700
Data Index: 3344042 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.9395. Min Act: -0.1700
Data Index: 5431254 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.9083. Min Act: -0.1700
Data Index: 7526492 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.9083. Min Act: -0.1700
Data Index: 2411413 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.8770. Min Act: -0.1700
Data Index: 2750452 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.8458. Min Act: -0.1700
Data Index: 4927491 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.8458. Min Act: -0.1700
Data Index: 5922107 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.8770. Min Act: -0.1700
Data Index: 4057842 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.8770. Min Act: -0.1700
Data Index: 6959993 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.8770. Min Act: -0.1700
Data Index: 2330326 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.8145. Min Act: -0.1700
Data Index: 3304927 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.8145. Min Act: -0.1700
Data Index: 5174961 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.7833. Min Act: -0.1700
Data Index: 1670557 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.8145. Min Act: -0.1700
Data Index: 1060827 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2520. Min Range: -5.2520
Max Act: 4.8145. Min Act: -0.1700
Data Index: 7369238 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19