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

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

Neuron 182 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2671. Min Range: -4.2671

Max Act: 3.7621. Min Act: -0.0000

Data Index: 1005974 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.2671. Min Act: -0.0000

Data Index: 1210531 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 4.2671. Min Range: -4.2671

Max Act: 3.7000. Min Act: -0.0000

Data Index: 541250 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 4.2671. Min Range: -4.2671

Max Act: 3.7403. Min Act: -0.0000

Data Index: 1020810 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 4.2671. Min Range: -4.2671

Max Act: 3.1356. Min Act: -0.0000

Data Index: 617639 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.9719. Min Act: -0.0000

Data Index: 1201899 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.9702. Min Act: -0.0000

Data Index: 348321 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.7233. Min Act: -0.0000

Data Index: 449005 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.3477. Min Act: -0.0000

Data Index: 1244002 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 4.2671. Min Range: -4.2671

Max Act: 3.0624. Min Act: -0.0000

Data Index: 1330501 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.9072. Min Act: -0.0000

Data Index: 287264 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.7507. Min Act: -0.0000

Data Index: 161408 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.6035. Min Act: -0.0000

Data Index: 1308511 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.5994. Min Act: -0.0000

Data Index: 1081793 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.7027. Min Act: -0.0000

Data Index: 120307 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.5429. Min Act: -0.0000

Data Index: 563672 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.4696. Min Act: -0.0000

Data Index: 23668 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.5358. Min Act: -0.0000

Data Index: 566710 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.1587. Min Act: -0.0000

Data Index: 664994 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 4.2671. Min Range: -4.2671

Max Act: 2.7173. Min Act: -0.0000

Data Index: 558830 (C4 (Web Text))

Max Activating Token Index: 174