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

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

Neuron 4238 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.9971. Min Act: -0.0000

Data Index: 1193380 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.6622. Min Act: -0.0001

Data Index: 755716 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.5358. Min Act: -0.0000

Data Index: 996182 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.4392. Min Act: -0.0000

Data Index: 116423 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.4750. Min Act: -0.0000

Data Index: 899128 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.4871. Min Act: -0.0000

Data Index: 923153 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.4261. Min Act: -0.0000

Data Index: 1167271 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.5070. Min Act: -0.0001

Data Index: 1315720 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.3860. Min Act: -0.0000

Data Index: 1176893 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.3368. Min Act: -0.0000

Data Index: 769228 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.2330. Min Act: -0.0001

Data Index: 413340 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.2201. Min Act: -0.0001

Data Index: 218630 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.2534. Min Act: -0.0001

Data Index: 863535 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1294887 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1190703 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.2678. Min Act: -0.0001

Data Index: 1015996 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1046918 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1105964 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.2419. Min Act: -0.0001

Data Index: 950890 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.9971. Min Range: -1.9971

Max Act: 1.1323. Min Act: -0.0001

Data Index: 767702 (C4 (Web Text))

Max Activating Token Index: 181