Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 88 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3588. Min Act: -0.0004

Data Index: 683502 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3250. Min Act: -0.0004

Data Index: 543139 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3216. Min Act: -0.0004

Data Index: 646452 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3113. Min Act: -0.0004

Data Index: 337011 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3209. Min Act: -0.0004

Data Index: 1344772 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3316. Min Act: -0.0004

Data Index: 536468 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3276. Min Act: -0.0004

Data Index: 52403 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3270. Min Act: -0.0004

Data Index: 1022722 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3145. Min Act: -0.0004

Data Index: 662776 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3261. Min Act: -0.0004

Data Index: 736604 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3483. Min Act: -0.0004

Data Index: 804125 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3253. Min Act: -0.0004

Data Index: 847980 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3247. Min Act: -0.0004

Data Index: 36624 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3136. Min Act: -0.0004

Data Index: 1270765 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3259. Min Act: -0.0004

Data Index: 1118115 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3239. Min Act: -0.0004

Data Index: 1063618 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3358. Min Act: -0.0004

Data Index: 998333 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3239. Min Act: -0.0004

Data Index: 302154 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3144. Min Act: -0.0004

Data Index: 303967 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3236. Min Act: -0.0004

Data Index: 162041 (C4 (Web Text))

Max Activating Token Index: 90