Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 515 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.6671. Min Act: -0.0001

Data Index: 1053816 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.3735. Min Act: -0.0001

Data Index: 901646 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.3527. Min Act: -0.0000

Data Index: 850706 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.3706. Min Act: -0.0000

Data Index: 578849 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.3629. Min Act: -0.0000

Data Index: 119680 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.3587. Min Act: -0.0000

Data Index: 514780 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.3102. Min Act: -0.0000

Data Index: 148020 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.3315. Min Act: -0.0001

Data Index: 1332321 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.2121. Min Act: -0.0000

Data Index: 599535 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.2300. Min Act: -0.0001

Data Index: 1000269 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.2220. Min Act: -0.0000

Data Index: 1134199 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.2020. Min Act: -0.0001

Data Index: 666844 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.1381. Min Act: -0.0000

Data Index: 1018659 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.1676. Min Act: -0.0000

Data Index: 849443 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.1189. Min Act: -0.0001

Data Index: 301429 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1254514 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.1396. Min Act: -0.0000

Data Index: 1284733 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.0948. Min Act: -0.0000

Data Index: 416627 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.1141. Min Act: -0.0000

Data Index: 304941 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.0565. Min Act: -0.0000

Data Index: 193561 (C4 (Web Text))

Max Activating Token Index: 673