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

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

Neuron 5072 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: 1.0365. Min Range: -1.0365

Max Act: 1.0365. Min Act: -0.0000

Data Index: 1089579 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 1.0365. Min Range: -1.0365

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1321833 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7524. Min Act: -0.0000

Data Index: 129363 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7839. Min Act: -0.0000

Data Index: 374312 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7344. Min Act: -0.0000

Data Index: 783750 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7257. Min Act: -0.0000

Data Index: 664966 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1285160 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1143450 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5371. Min Act: -0.0000

Data Index: 661254 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5107. Min Act: -0.0000

Data Index: 639721 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1060375 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5313. Min Act: -0.0000

Data Index: 289907 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1124508 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.4739. Min Act: -0.0000

Data Index: 632641 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.4738. Min Act: -0.0000

Data Index: 50032 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.4784. Min Act: -0.0000

Data Index: 566582 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.4614. Min Act: -0.0000

Data Index: 468790 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.4842. Min Act: -0.0000

Data Index: 893200 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.4365. Min Act: -0.0000

Data Index: 344085 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1136243 (C4 (Web Text))

Max Activating Token Index: 452