Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3368 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.2459. Min Act: -0.0000

Data Index: 1294909 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.2053. Min Act: -0.0000

Data Index: 1122662 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.1030. Min Act: -0.0000

Data Index: 5615 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.2027. Min Act: -0.0000

Data Index: 459911 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.1851. Min Act: -0.0000

Data Index: 306730 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.1748. Min Act: -0.0000

Data Index: 284771 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.1487. Min Act: -0.0000

Data Index: 1028951 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1249477 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.0565. Min Act: -0.0000

Data Index: 688764 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 1.2459. Min Range: -1.2459

Max Act: 1.0399. Min Act: -0.0000

Data Index: 565997 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.9204. Min Act: -0.0000

Data Index: 856057 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.9508. Min Act: -0.0000

Data Index: 661719 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.8288. Min Act: -0.0000

Data Index: 995386 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.8316. Min Act: -0.0000

Data Index: 350886 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.8112. Min Act: -0.0000

Data Index: 954097 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1174738 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1057474 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.7335. Min Act: -0.0000

Data Index: 323305 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.7252. Min Act: -0.0000

Data Index: 391389 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 1.2459. Min Range: -1.2459

Max Act: 0.7956. Min Act: -0.0000

Data Index: 382618 (C4 (Web Text))

Max Activating Token Index: 592