Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3112 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.4597. Min Act: -0.0000

Data Index: 39070 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1289781 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3934. Min Act: -0.0000

Data Index: 141598 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3821. Min Act: -0.0000

Data Index: 527955 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1185037 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3459. Min Act: -0.0000

Data Index: 67370 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1348120 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3671. Min Act: -0.0000

Data Index: 276259 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3583. Min Act: -0.0000

Data Index: 574623 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3531. Min Act: -0.0000

Data Index: 205900 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3155. Min Act: -0.0000

Data Index: 307889 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1209524 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3263. Min Act: -0.0000

Data Index: 228490 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3334. Min Act: -0.0000

Data Index: 24861 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1001897 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1332599 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3517. Min Act: -0.0000

Data Index: 336844 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3609. Min Act: -0.0000

Data Index: 879640 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3046. Min Act: -0.0000

Data Index: 507976 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2901. Min Act: -0.0000

Data Index: 109081 (C4 (Web Text))

Max Activating Token Index: 567