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

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

Neuron 4838 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.8862. Min Act: -0.0000

Data Index: 675027 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.8106. Min Act: -0.0000

Data Index: 156090 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.7840. Min Act: -0.0000

Data Index: 934054 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.8029. Min Act: -0.0000

Data Index: 831941 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.7281. Min Act: -0.0000

Data Index: 838434 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1140165 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.7067. Min Act: -0.0000

Data Index: 976962 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6942. Min Act: -0.0000

Data Index: 926843 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6743. Min Act: -0.0000

Data Index: 577371 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6169. Min Act: -0.0000

Data Index: 591347 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6642. Min Act: -0.0000

Data Index: 585088 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6103. Min Act: -0.0000

Data Index: 305050 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6481. Min Act: -0.0000

Data Index: 30597 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6413. Min Act: -0.0000

Data Index: 16083 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1274186 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1267905 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6097. Min Act: -0.0000

Data Index: 524770 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5865. Min Act: -0.0000

Data Index: 299053 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5829. Min Act: -0.0000

Data Index: 78312 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1111358 (C4 (Web Text))

Max Activating Token Index: 85