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

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

Neuron 4408 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: 3.9028. Min Range: -3.9028

Max Act: 3.9028. Min Act: -0.0000

Data Index: 1176136 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.8418. Min Act: -0.0000

Data Index: 1173229 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7154. Min Act: -0.0000

Data Index: 335033 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.5297. Min Act: -0.0000

Data Index: 1095827 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.3322. Min Act: -0.0000

Data Index: 1213003 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.2205. Min Act: -0.0000

Data Index: 1343024 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.3543. Min Act: -0.0000

Data Index: 1319007 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.3253. Min Act: -0.0000

Data Index: 1339688 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.0877. Min Act: -0.0000

Data Index: 1056827 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1919. Min Act: -0.0000

Data Index: 1065447 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1632. Min Act: -0.0000

Data Index: 1078250 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.2513. Min Act: -0.0000

Data Index: 542952 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1834. Min Act: -0.0000

Data Index: 934678 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.0050. Min Act: -0.0000

Data Index: 1169302 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.0305. Min Act: -0.0000

Data Index: 188496 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.0059. Min Act: -0.0000

Data Index: 1369978 (Python Code)

Max Activating Token Index: 769

Text #16

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1576. Min Act: -0.0000

Data Index: 811017 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1532. Min Act: -0.0000

Data Index: 949571 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1082. Min Act: -0.0000

Data Index: 854443 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.2501. Min Act: -0.0000

Data Index: 498967 (C4 (Web Text))

Max Activating Token Index: 663