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

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

Neuron 3572 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0968. Min Range: -1.0968

Max Act: 1.0968. Min Act: -0.0002

Data Index: 459098 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.0968. Min Range: -1.0968

Max Act: 1.0224. Min Act: -0.0002

Data Index: 1267099 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 1.0968. Min Range: -1.0968

Max Act: 1.0255. Min Act: -0.0002

Data Index: 1206424 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.0968. Min Range: -1.0968

Max Act: 1.0036. Min Act: -0.0002

Data Index: 658779 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 1.0968. Min Range: -1.0968

Max Act: 1.0046. Min Act: -0.0002

Data Index: 162571 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9623. Min Act: -0.0002

Data Index: 234965 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9713. Min Act: -0.0002

Data Index: 191730 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9459. Min Act: -0.0002

Data Index: 792825 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9652. Min Act: -0.0002

Data Index: 1393146 (Python Code)

Max Activating Token Index: 128

Text #9

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9640. Min Act: -0.0002

Data Index: 1283570 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9569. Min Act: -0.0003

Data Index: 702150 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9380. Min Act: -0.0002

Data Index: 1353932 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9456. Min Act: -0.0002

Data Index: 857929 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9701. Min Act: -0.0002

Data Index: 1149463 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9453. Min Act: -0.0002

Data Index: 923559 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9233. Min Act: -0.0002

Data Index: 370816 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9266. Min Act: -0.0002

Data Index: 1330575 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9287. Min Act: -0.0002

Data Index: 800414 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9022. Min Act: -0.0002

Data Index: 1077432 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9146. Min Act: -0.0002

Data Index: 621743 (C4 (Web Text))

Max Activating Token Index: 377