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

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

Neuron 4677 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: 2.0527. Min Range: -2.0527

Max Act: 2.0527. Min Act: -0.0000

Data Index: 1114609 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.8938. Min Act: -0.0000

Data Index: 361575 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.8537. Min Act: -0.0000

Data Index: 386652 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.7306. Min Act: -0.0000

Data Index: 452371 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.7823. Min Act: -0.0000

Data Index: 243536 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.7173. Min Act: -0.0000

Data Index: 943039 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.6407. Min Act: -0.0000

Data Index: 1149982 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.5944. Min Act: -0.0000

Data Index: 23194 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.5936. Min Act: -0.0000

Data Index: 1193922 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.5796. Min Act: -0.0000

Data Index: 1278048 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.5268. Min Act: -0.0000

Data Index: 191153 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.5032. Min Act: -0.0000

Data Index: 78083 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.4844. Min Act: -0.0000

Data Index: 65423 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.4661. Min Act: -0.0000

Data Index: 534751 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.3716. Min Act: -0.0000

Data Index: 396110 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.3564. Min Act: -0.0000

Data Index: 1130664 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.5234. Min Act: -0.0000

Data Index: 1269884 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.4238. Min Act: -0.0000

Data Index: 810046 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.3423. Min Act: -0.0000

Data Index: 1211083 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 2.0527. Min Range: -2.0527

Max Act: 1.4337. Min Act: -0.0000

Data Index: 1142818 (C4 (Web Text))

Max Activating Token Index: 216