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

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

Neuron 3145 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0154. Min Range: -2.0154

Max Act: 2.0154. Min Act: -0.0000

Data Index: 521795 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 2.0154. Min Range: -2.0154

Max Act: 1.8866. Min Act: -0.0000

Data Index: 396202 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 2.0154. Min Range: -2.0154

Max Act: 1.7457. Min Act: -0.0000

Data Index: 754206 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 2.0154. Min Range: -2.0154

Max Act: 1.0840. Min Act: -0.0000

Data Index: 345928 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 2.0154. Min Range: -2.0154

Max Act: 1.0412. Min Act: -0.0000

Data Index: 740944 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 2.0154. Min Range: -2.0154

Max Act: 1.0211. Min Act: -0.0000

Data Index: 581521 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.9512. Min Act: -0.0000

Data Index: 120074 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.9321. Min Act: -0.0000

Data Index: 126136 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1450048 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1282195 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.8237. Min Act: -0.0000

Data Index: 381826 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.8265. Min Act: -0.0000

Data Index: 235993 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.8071. Min Act: -0.0000

Data Index: 9556 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.7745. Min Act: -0.0000

Data Index: 273264 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.8021. Min Act: -0.0000

Data Index: 846155 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.8238. Min Act: -0.0000

Data Index: 721497 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.7832. Min Act: 0.0000

Data Index: 695181 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.8113. Min Act: -0.0000

Data Index: 945136 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1037342 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 2.0154. Min Range: -2.0154

Max Act: 0.7944. Min Act: -0.0000

Data Index: 977658 (C4 (Web Text))

Max Activating Token Index: 525