Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4311. Min Range: -7.4311
Max Act: 7.4311. Min Act: -0.1700
Data Index: 5220222 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4311. Min Range: -7.4311
Max Act: 7.3998. Min Act: -0.1700
Data Index: 5903548 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4311. Min Range: -7.4311
Max Act: 7.3686. Min Act: -0.1700
Data Index: 1894374 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4311. Min Range: -7.4311
Max Act: 7.0561. Min Act: -0.1700
Data Index: 5903549 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4311. Min Range: -7.4311
Max Act: 7.0248. Min Act: -0.1700
Data Index: 5220224 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.9936. Min Act: -0.1700
Data Index: 8538085 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4311. Min Range: -7.4311
Max Act: 7.0248. Min Act: -0.1700
Data Index: 5220223 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.6811. Min Act: -0.1700
Data Index: 6533439 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.6811. Min Act: -0.1700
Data Index: 5903550 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.6498. Min Act: -0.1700
Data Index: 4220691 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.6498. Min Act: -0.1700
Data Index: 7518887 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.6498. Min Act: -0.1700
Data Index: 1071689 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.5873. Min Act: -0.1700
Data Index: 2158959 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.5873. Min Act: -0.1700
Data Index: 7666182 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.5873. Min Act: -0.1700
Data Index: 6118575 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.6186. Min Act: -0.1700
Data Index: 1226709 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.5248. Min Act: -0.1700
Data Index: 8277449 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.5561. Min Act: -0.1700
Data Index: 5722560 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.4936. Min Act: -0.1700
Data Index: 8483776 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4311. Min Range: -7.4311
Max Act: 6.4623. Min Act: -0.1700
Data Index: 3702175 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19