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

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

Neuron 1519 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3224. Min Act: -0.0000

Data Index: 549973 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3210. Min Act: -0.0000

Data Index: 164217 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3069. Min Act: -0.0000

Data Index: 837706 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3054. Min Act: -0.0000

Data Index: 603047 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2950. Min Act: -0.0000

Data Index: 938748 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2736. Min Act: -0.0000

Data Index: 98266 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2971. Min Act: -0.0000

Data Index: 697390 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3198. Min Act: -0.0000

Data Index: 265126 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2997. Min Act: -0.0000

Data Index: 417447 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2816. Min Act: -0.0000

Data Index: 874270 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2906. Min Act: -0.0000

Data Index: 35831 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1017181 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2562. Min Act: -0.0000

Data Index: 522886 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1257048 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2618. Min Act: -0.0000

Data Index: 55246 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2536. Min Act: -0.0000

Data Index: 704617 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2918. Min Act: -0.0000

Data Index: 980689 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1034360 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2635. Min Act: -0.0000

Data Index: 984572 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1297257 (C4 (Web Text))

Max Activating Token Index: 552