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

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

Neuron 4678 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2151. Min Range: -1.2151

Max Act: 1.2151. Min Act: -0.0000

Data Index: 205549 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 1.2151. Min Range: -1.2151

Max Act: 1.1116. Min Act: -0.0000

Data Index: 270698 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 1.2151. Min Range: -1.2151

Max Act: 1.1452. Min Act: -0.0000

Data Index: 266358 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 1.2151. Min Range: -1.2151

Max Act: 1.0644. Min Act: -0.0000

Data Index: 641945 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.9926. Min Act: -0.0000

Data Index: 195084 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.9096. Min Act: -0.0000

Data Index: 794098 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.9330. Min Act: -0.0000

Data Index: 995966 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.9312. Min Act: -0.0000

Data Index: 172530 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.8996. Min Act: -0.0000

Data Index: 394160 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.8929. Min Act: -0.0000

Data Index: 496878 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.8823. Min Act: -0.0000

Data Index: 448270 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.8799. Min Act: -0.0000

Data Index: 190626 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.8550. Min Act: -0.0000

Data Index: 626415 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.8234. Min Act: -0.0000

Data Index: 446152 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.8418. Min Act: -0.0000

Data Index: 939085 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1313205 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1290676 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1096701 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.8249. Min Act: -0.0000

Data Index: 639537 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 1.2151. Min Range: -1.2151

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1359431 (C4 (Web Text))

Max Activating Token Index: 152