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

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

Neuron 66 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2963. Min Act: -0.0001

Data Index: 704181 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2688. Min Act: -0.0000

Data Index: 394069 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2683. Min Act: 0.0002

Data Index: 1126251 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2537. Min Act: 0.0000

Data Index: 716933 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2538. Min Act: 0.0003

Data Index: 898171 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2420. Min Act: 0.0003

Data Index: 156144 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2429. Min Act: -0.0001

Data Index: 396639 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2470. Min Act: -0.0001

Data Index: 873343 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2242. Min Act: -0.0001

Data Index: 890038 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2342. Min Act: -0.0001

Data Index: 1305041 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2345. Min Act: -0.0001

Data Index: 679050 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2328. Min Act: -0.0000

Data Index: 932097 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2308. Min Act: -0.0001

Data Index: 297858 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2272. Min Act: -0.0000

Data Index: 98024 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2237. Min Act: -0.0001

Data Index: 1268672 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2162. Min Act: -0.0001

Data Index: 730706 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2175. Min Act: -0.0000

Data Index: 344500 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2231. Min Act: -0.0000

Data Index: 653175 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2225. Min Act: -0.0000

Data Index: 793094 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2225. Min Act: -0.0001

Data Index: 323617 (C4 (Web Text))

Max Activating Token Index: 937