Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1432 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.5287. Min Act: -0.1700
Data Index: 3938320 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.1537. Min Act: -0.1700
Data Index: 4917751 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.1849. Min Act: -0.1700
Data Index: 114442 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.1537. Min Act: -0.1700
Data Index: 1330535 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.1224. Min Act: -0.1700
Data Index: 8215247 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.0912. Min Act: -0.1700
Data Index: 3673657 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.0912. Min Act: -0.1700
Data Index: 7298633 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.0912. Min Act: -0.1700
Data Index: 1494635 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.9662. Min Act: -0.1700
Data Index: 2710499 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.9349. Min Act: -0.1700
Data Index: 4746930 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.9662. Min Act: -0.1700
Data Index: 2559707 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.9662. Min Act: -0.1700
Data Index: 2335868 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.9349. Min Act: -0.1700
Data Index: 6478828 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.9349. Min Act: -0.1700
Data Index: 4929236 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.9037. Min Act: -0.1700
Data Index: 2497446 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.8724. Min Act: -0.1700
Data Index: 7035346 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.9037. Min Act: -0.1700
Data Index: 8782851 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.9037. Min Act: -0.1700
Data Index: 802438 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.9037. Min Act: -0.1700
Data Index: 2265726 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5287. Min Range: -6.5287
Max Act: 5.8412. Min Act: -0.1700
Data Index: 1699770 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19