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

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

Neuron 216 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: 0.3589. Min Range: -0.3589

Max Act: 0.3303. Min Act: -0.0001

Data Index: 148747 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3258. Min Act: -0.0001

Data Index: 441811 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3359. Min Act: -0.0001

Data Index: 1452045 (Python Code)

Max Activating Token Index: 596

Text #3

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3381. Min Act: -0.0001

Data Index: 1376511 (Python Code)

Max Activating Token Index: 601

Text #4

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3198. Min Act: -0.0001

Data Index: 498280 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3291. Min Act: -0.0001

Data Index: 466413 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3589. Min Act: -0.0001

Data Index: 1263923 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3248. Min Act: -0.0001

Data Index: 35155 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3210. Min Act: -0.0001

Data Index: 483637 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3157. Min Act: -0.0001

Data Index: 3509 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2928. Min Act: -0.0001

Data Index: 70067 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3192. Min Act: -0.0001

Data Index: 1320686 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2935. Min Act: -0.0001

Data Index: 893496 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3021. Min Act: -0.0001

Data Index: 228319 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2831. Min Act: -0.0001

Data Index: 1251193 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2918. Min Act: -0.0001

Data Index: 77074 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2671. Min Act: -0.0001

Data Index: 434627 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2833. Min Act: -0.0001

Data Index: 884380 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2765. Min Act: -0.0001

Data Index: 286823 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1249206 (C4 (Web Text))

Max Activating Token Index: 122