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

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

Neuron 530 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: 2.3567. Min Range: -2.3567

Max Act: 2.3567. Min Act: -0.0000

Data Index: 781279 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 2.3567. Min Range: -2.3567

Max Act: 2.3102. Min Act: -0.0001

Data Index: 541495 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 2.3567. Min Range: -2.3567

Max Act: 2.1953. Min Act: -0.0000

Data Index: 852499 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.9941. Min Act: -0.0000

Data Index: 157415 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.9341. Min Act: -0.0001

Data Index: 1320027 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.9125. Min Act: -0.0001

Data Index: 1555736 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.8451. Min Act: -0.0000

Data Index: 788150 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.8216. Min Act: -0.0001

Data Index: 969264 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.8129. Min Act: -0.0001

Data Index: 1108747 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.7331. Min Act: -0.0001

Data Index: 224941 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.7685. Min Act: -0.0000

Data Index: 316914 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.8043. Min Act: -0.0001

Data Index: 125991 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.7834. Min Act: -0.0000

Data Index: 1097599 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.7151. Min Act: -0.0000

Data Index: 864060 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.6983. Min Act: -0.0000

Data Index: 367306 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.7002. Min Act: -0.0000

Data Index: 421390 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.6430. Min Act: -0.0000

Data Index: 1104347 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.7443. Min Act: -0.0000

Data Index: 1125019 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.6147. Min Act: -0.0000

Data Index: 117963 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.7165. Min Act: -0.0000

Data Index: 449617 (C4 (Web Text))

Max Activating Token Index: 500