Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3271 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.8596. Min Act: -0.0000

Data Index: 747664 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.7953. Min Act: -0.0000

Data Index: 780407 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.7288. Min Act: -0.0000

Data Index: 651119 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6806. Min Act: -0.0000

Data Index: 195812 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1099811 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6709. Min Act: -0.0000

Data Index: 493311 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6214. Min Act: -0.0000

Data Index: 800328 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6790. Min Act: -0.0000

Data Index: 316071 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5726. Min Act: 0.0000

Data Index: 12412 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5969. Min Act: -0.0000

Data Index: 34532 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6328. Min Act: -0.0000

Data Index: 171508 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6053. Min Act: -0.0000

Data Index: 129110 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5728. Min Act: -0.0000

Data Index: 433479 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5355. Min Act: -0.0000

Data Index: 607689 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5327. Min Act: -0.0000

Data Index: 366930 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5503. Min Act: -0.0000

Data Index: 105850 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5645. Min Act: -0.0000

Data Index: 568980 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5274. Min Act: -0.0000

Data Index: 381550 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5235. Min Act: -0.0000

Data Index: 131304 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5343. Min Act: -0.0000

Data Index: 376028 (C4 (Web Text))

Max Activating Token Index: 278