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

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

Neuron 4348 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.6808. Min Act: -0.0000

Data Index: 937344 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.6077. Min Act: -0.0000

Data Index: 729506 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.5174. Min Act: -0.0000

Data Index: 463514 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4714. Min Act: -0.0000

Data Index: 991011 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4130. Min Act: -0.0000

Data Index: 593244 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3967. Min Act: -0.0000

Data Index: 583668 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4046. Min Act: -0.0000

Data Index: 163875 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1061590 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3755. Min Act: -0.0000

Data Index: 601246 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3755. Min Act: -0.0000

Data Index: 214865 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3687. Min Act: -0.0000

Data Index: 772287 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3466. Min Act: -0.0000

Data Index: 442186 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3458. Min Act: -0.0000

Data Index: 353087 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3801. Min Act: -0.0000

Data Index: 999073 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1027432 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3392. Min Act: -0.0000

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3489. Min Act: -0.0000

Data Index: 236304 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3298. Min Act: -0.0000

Data Index: 131756 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3310. Min Act: -0.0000

Data Index: 517963 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.3341. Min Act: -0.0000

Data Index: 734272 (C4 (Web Text))

Max Activating Token Index: 321