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

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

Neuron 3474 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: 1.7967. Min Range: -1.7967

Max Act: 1.7349. Min Act: -0.0000

Data Index: 996927 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.7967. Min Act: -0.0000

Data Index: 850393 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.5422. Min Act: -0.0000

Data Index: 1242150 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.5970. Min Act: -0.0000

Data Index: 1350991 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1354975 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.5403. Min Act: -0.0000

Data Index: 415492 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.6195. Min Act: -0.0000

Data Index: 139622 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.4925. Min Act: -0.0000

Data Index: 598365 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.4672. Min Act: -0.0000

Data Index: 1008632 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.4545. Min Act: -0.0000

Data Index: 387486 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.4414. Min Act: -0.0000

Data Index: 29756 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.4235. Min Act: -0.0000

Data Index: 388232 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.3968. Min Act: -0.0000

Data Index: 23567 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.3934. Min Act: -0.0000

Data Index: 745256 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1324881 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.3542. Min Act: -0.0000

Data Index: 998286 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.2821. Min Act: -0.0000

Data Index: 293455 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.2622. Min Act: 0.0000

Data Index: 460561 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.1628. Min Act: -0.0000

Data Index: 366315 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 1.7967. Min Range: -1.7967

Max Act: 1.1593. Min Act: -0.0000

Data Index: 347236 (C4 (Web Text))

Max Activating Token Index: 538