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

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

Neuron 4336 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.5022. Min Act: -0.0000

Data Index: 329573 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.3364. Min Act: -0.0000

Data Index: 355598 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.3048. Min Act: -0.0000

Data Index: 347083 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.2533. Min Act: -0.0000

Data Index: 654271 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.2200. Min Act: -0.0000

Data Index: 599566 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.2089. Min Act: -0.0000

Data Index: 382932 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1213770 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1359113 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.1310. Min Act: -0.0000

Data Index: 261585 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.1949. Min Act: -0.0000

Data Index: 436258 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.1161. Min Act: -0.0000

Data Index: 1311090 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0747. Min Act: -0.0000

Data Index: 423347 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.1316. Min Act: -0.0000

Data Index: 982350 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0869. Min Act: -0.0000

Data Index: 146049 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0469. Min Act: -0.0000

Data Index: 432512 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1590398 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0843. Min Act: -0.0000

Data Index: 792556 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1312733 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0789. Min Act: -0.0000

Data Index: 657002 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0305. Min Act: -0.0000

Data Index: 1438653 (Python Code)

Max Activating Token Index: 437