Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3718 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3388. Min Range: -7.3388
Max Act: 7.3388. Min Act: -0.1700
Data Index: 5379375 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3388. Min Range: -7.3388
Max Act: 7.2763. Min Act: -0.1700
Data Index: 6819528 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3388. Min Range: -7.3388
Max Act: 7.1513. Min Act: -0.1700
Data Index: 7070460 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3388. Min Range: -7.3388
Max Act: 7.1513. Min Act: -0.1700
Data Index: 5856431 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3388. Min Range: -7.3388
Max Act: 7.0888. Min Act: -0.1700
Data Index: 804741 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3388. Min Range: -7.3388
Max Act: 7.0575. Min Act: -0.1700
Data Index: 1054636 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3388. Min Range: -7.3388
Max Act: 7.0263. Min Act: -0.1700
Data Index: 7494577 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3388. Min Range: -7.3388
Max Act: 7.0263. Min Act: -0.1700
Data Index: 702183 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3388. Min Range: -7.3388
Max Act: 7.0575. Min Act: -0.1700
Data Index: 4462082 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3388. Min Range: -7.3388
Max Act: 6.9950. Min Act: -0.1700
Data Index: 4601444 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3388. Min Range: -7.3388
Max Act: 6.9950. Min Act: -0.1700
Data Index: 1062853 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3388. Min Range: -7.3388
Max Act: 6.9325. Min Act: -0.1700
Data Index: 6395157 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3388. Min Range: -7.3388
Max Act: 6.9325. Min Act: -0.1700
Data Index: 7204873 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3388. Min Range: -7.3388
Max Act: 6.9325. Min Act: -0.1700
Data Index: 8805776 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3388. Min Range: -7.3388
Max Act: 6.9325. Min Act: -0.1700
Data Index: 927974 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3388. Min Range: -7.3388
Max Act: 6.9013. Min Act: -0.1700
Data Index: 7756764 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3388. Min Range: -7.3388
Max Act: 6.9013. Min Act: -0.1700
Data Index: 3513910 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3388. Min Range: -7.3388
Max Act: 6.9013. Min Act: -0.1700
Data Index: 5724975 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3388. Min Range: -7.3388
Max Act: 6.9013. Min Act: -0.1700
Data Index: 3706876 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3388. Min Range: -7.3388
Max Act: 6.9013. Min Act: -0.1700
Data Index: 6079355 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19