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

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

Neuron 5427 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2299. Min Range: -2.2299

Max Act: 2.2299. Min Act: -0.0000

Data Index: 1047014 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 2.2299. Min Range: -2.2299

Max Act: 2.1533. Min Act: -0.0000

Data Index: 52255 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 2.2299. Min Range: -2.2299

Max Act: 2.0895. Min Act: -0.0000

Data Index: 603126 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.9673. Min Act: 0.0000

Data Index: 613491 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.9656. Min Act: -0.0000

Data Index: 975712 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.9679. Min Act: -0.0000

Data Index: 942814 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.9384. Min Act: -0.0000

Data Index: 1128823 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.9420. Min Act: -0.0000

Data Index: 430603 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.9432. Min Act: -0.0000

Data Index: 66485 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.9205. Min Act: -0.0000

Data Index: 1149579 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.8959. Min Act: 0.0000

Data Index: 1293907 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.9006. Min Act: -0.0000

Data Index: 340636 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.8410. Min Act: -0.0000

Data Index: 465564 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.8290. Min Act: 0.0001

Data Index: 1302294 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.8143. Min Act: -0.0000

Data Index: 1218297 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.8009. Min Act: -0.0000

Data Index: 482813 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.7629. Min Act: -0.0000

Data Index: 939585 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.7595. Min Act: -0.0000

Data Index: 865761 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.8279. Min Act: -0.0000

Data Index: 30215 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 2.2299. Min Range: -2.2299

Max Act: 1.7263. Min Act: -0.0000

Data Index: 564518 (C4 (Web Text))

Max Activating Token Index: 506