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

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

Neuron 2984 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: 3.1230. Min Range: -3.1230

Max Act: 3.1230. Min Act: -0.0000

Data Index: 573180 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 3.1230. Min Range: -3.1230

Max Act: 2.1134. Min Act: -0.0000

Data Index: 576221 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 3.1230. Min Range: -3.1230

Max Act: 2.2489. Min Act: -0.0000

Data Index: 1308089 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 3.1230. Min Range: -3.1230

Max Act: 2.0155. Min Act: -0.0000

Data Index: 640971 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 3.1230. Min Range: -3.1230

Max Act: 2.0062. Min Act: -0.0000

Data Index: 1590314 (Python Code)

Max Activating Token Index: 205

Text #5

Max Range: 3.1230. Min Range: -3.1230

Max Act: 2.0975. Min Act: -0.0000

Data Index: 990137 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.9787. Min Act: -0.0000

Data Index: 25897 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 3.1230. Min Range: -3.1230

Max Act: 2.0493. Min Act: -0.0000

Data Index: 1336259 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.9268. Min Act: -0.0000

Data Index: 1292208 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.9346. Min Act: -0.0000

Data Index: 194788 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.8028. Min Act: -0.0000

Data Index: 1225603 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.9971. Min Act: -0.0000

Data Index: 1269720 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.9773. Min Act: -0.0000

Data Index: 345729 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.9813. Min Act: -0.0000

Data Index: 168100 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.8523. Min Act: -0.0000

Data Index: 632410 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.7173. Min Act: -0.0000

Data Index: 1512578 (Python Code)

Max Activating Token Index: 270

Text #16

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.8205. Min Act: -0.0000

Data Index: 537249 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.7995. Min Act: -0.0000

Data Index: 1425599 (Python Code)

Max Activating Token Index: 426

Text #18

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.6930. Min Act: 0.0000

Data Index: 117161 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 3.1230. Min Range: -3.1230

Max Act: 1.7488. Min Act: -0.0000

Data Index: 1439943 (Python Code)

Max Activating Token Index: 802