Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1841 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2474. Min Range: -6.2474
Max Act: 6.2474. Min Act: -0.1700
Data Index: 8089861 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2474. Min Range: -6.2474
Max Act: 6.1224. Min Act: -0.1700
Data Index: 2874053 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2474. Min Range: -6.2474
Max Act: 6.1224. Min Act: -0.1700
Data Index: 2268222 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2474. Min Range: -6.2474
Max Act: 6.0912. Min Act: -0.1700
Data Index: 7427841 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2474. Min Range: -6.2474
Max Act: 6.0912. Min Act: -0.1700
Data Index: 2608973 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2474. Min Range: -6.2474
Max Act: 6.0912. Min Act: -0.1700
Data Index: 2327195 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2474. Min Range: -6.2474
Max Act: 6.1224. Min Act: -0.1700
Data Index: 2543496 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2474. Min Range: -6.2474
Max Act: 6.0912. Min Act: -0.1700
Data Index: 4603014 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9974. Min Act: -0.1700
Data Index: 3941847 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9974. Min Act: -0.1700
Data Index: 3087800 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9974. Min Act: -0.1700
Data Index: 3700473 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9974. Min Act: -0.1700
Data Index: 5716712 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9974. Min Act: -0.1700
Data Index: 7257781 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9974. Min Act: -0.1700
Data Index: 4949549 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9662. Min Act: -0.1700
Data Index: 990315 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9662. Min Act: -0.1700
Data Index: 5740064 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9662. Min Act: -0.1700
Data Index: 5943224 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9662. Min Act: -0.1700
Data Index: 7215725 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9037. Min Act: -0.1700
Data Index: 1421281 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2474. Min Range: -6.2474
Max Act: 5.9349. Min Act: -0.1700
Data Index: 1729463 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19