Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 345 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.4335. Min Act: -0.1700
Data Index: 3407535 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.3190. Min Act: -0.1700
Data Index: 2411310 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.3190. Min Act: -0.1700
Data Index: 920452 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.3190. Min Act: -0.1700
Data Index: 1374227 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.3026. Min Act: -0.1700
Data Index: 2135176 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2861. Min Act: -0.1700
Data Index: 7409076 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2697. Min Act: -0.1700
Data Index: 3889808 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2697. Min Act: -0.1700
Data Index: 4833676 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2697. Min Act: -0.1700
Data Index: 3407536 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2532. Min Act: -0.1700
Data Index: 6655788 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2532. Min Act: -0.1700
Data Index: 6100002 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2532. Min Act: -0.1700
Data Index: 8313906 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2532. Min Act: -0.1700
Data Index: 906041 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2697. Min Act: -0.1700
Data Index: 5498213 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2532. Min Act: -0.1700
Data Index: 4286732 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2532. Min Act: -0.1700
Data Index: 1035032 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2366. Min Act: -0.1700
Data Index: 3100467 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2366. Min Act: -0.1700
Data Index: 2766397 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2366. Min Act: -0.1700
Data Index: 6621585 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4335. Min Range: -2.4335
Max Act: 2.2201. Min Act: -0.1700
Data Index: 7162909 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19