Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4048 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.9954. Min Act: -0.1700
Data Index: 10324 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.9641. Min Act: -0.1700
Data Index: 5381632 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.9016. Min Act: -0.1700
Data Index: 5757865 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.9016. Min Act: -0.1700
Data Index: 1132343 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.8391. Min Act: -0.1700
Data Index: 1740707 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.7141. Min Act: -0.1700
Data Index: 4332405 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.7141. Min Act: -0.1700
Data Index: 8456799 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.7141. Min Act: -0.1700
Data Index: 6556545 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.7454. Min Act: -0.1700
Data Index: 2258575 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.6516. Min Act: -0.1700
Data Index: 6968194 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.6829. Min Act: -0.1700
Data Index: 7491513 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.6204. Min Act: -0.1700
Data Index: 6707197 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.6516. Min Act: -0.1700
Data Index: 8435094 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.6204. Min Act: -0.1700
Data Index: 7319860 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.6204. Min Act: -0.1700
Data Index: 2848412 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.6204. Min Act: -0.1700
Data Index: 3073324 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.6204. Min Act: -0.1700
Data Index: 1677778 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.5891. Min Act: -0.1700
Data Index: 3681236 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.6204. Min Act: -0.1700
Data Index: 6444246 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9954. Min Range: -5.9954
Max Act: 5.6204. Min Act: -0.1700
Data Index: 168329 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19