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

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

Neuron 3110 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1270. Min Range: -2.1270

Max Act: 2.1270. Min Act: -0.0000

Data Index: 6119 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 2.1270. Min Range: -2.1270

Max Act: 2.0497. Min Act: -0.0000

Data Index: 308372 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.8299. Min Act: -0.0000

Data Index: 149503 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.6329. Min Act: -0.0000

Data Index: 50672 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.3258. Min Act: -0.0000

Data Index: 364230 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.2355. Min Act: -0.0000

Data Index: 392046 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.2910. Min Act: -0.0000

Data Index: 774095 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.1770. Min Act: -0.0000

Data Index: 1285046 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.2104. Min Act: -0.0000

Data Index: 124618 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.2535. Min Act: -0.0000

Data Index: 184158 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.2730. Min Act: -0.0000

Data Index: 855481 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1173195 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.1103. Min Act: -0.0000

Data Index: 455339 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.0993. Min Act: -0.0000

Data Index: 529338 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.2566. Min Act: -0.0000

Data Index: 1130813 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1323782 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.1416. Min Act: -0.0000

Data Index: 275712 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.1212. Min Act: -0.0000

Data Index: 307923 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.1563. Min Act: -0.0000

Data Index: 526005 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 2.1270. Min Range: -2.1270

Max Act: 1.1924. Min Act: -0.0000

Data Index: 704964 (C4 (Web Text))

Max Activating Token Index: 847