Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1461 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.6494. Min Act: -0.0001

Data Index: 706778 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.5671. Min Act: -0.0001

Data Index: 1213843 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.5642. Min Act: -0.0001

Data Index: 515915 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.4782. Min Act: -0.0001

Data Index: 85763 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.5069. Min Act: -0.0001

Data Index: 38358 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.4408. Min Act: -0.0000

Data Index: 1269204 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.4030. Min Act: -0.0001

Data Index: 1359409 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.4729. Min Act: -0.0001

Data Index: 449919 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.6494. Min Range: -1.6494

Max Act: 0.9413. Min Act: -0.0000

Data Index: 95314 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.0959. Min Act: -0.0000

Data Index: 1301447 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1141971 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1472. Min Act: -0.0001

Data Index: 1255868 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1567. Min Act: -0.0001

Data Index: 1488965 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2236. Min Act: -0.0000

Data Index: 89479 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2554. Min Act: -0.0001

Data Index: 523378 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1337130 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.0592. Min Act: -0.0001

Data Index: 954067 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.0616. Min Act: -0.0000

Data Index: 415010 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1619. Min Act: -0.0001

Data Index: 485074 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1585. Min Act: -0.0000

Data Index: 800089 (C4 (Web Text))

Max Activating Token Index: 220