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

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

Neuron 2208 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: 3.8775. Min Range: -3.8775

Max Act: 3.8775. Min Act: -0.0000

Data Index: 119981 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 3.8775. Min Range: -3.8775

Max Act: 3.6548. Min Act: -0.0000

Data Index: 298746 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 3.8775. Min Range: -3.8775

Max Act: 3.2071. Min Act: -0.0001

Data Index: 721399 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 3.8775. Min Range: -3.8775

Max Act: 3.2214. Min Act: -0.0000

Data Index: 1340061 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.9549. Min Act: -0.0000

Data Index: 62178 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.8747. Min Act: -0.0000

Data Index: 964184 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.6915. Min Act: -0.0000

Data Index: 217482 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.8001. Min Act: -0.0000

Data Index: 1340616 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.8147. Min Act: -0.0000

Data Index: 607718 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.8032. Min Act: -0.0000

Data Index: 1176790 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.7661. Min Act: -0.0000

Data Index: 1127138 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.7935. Min Act: -0.0001

Data Index: 198680 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.6295. Min Act: -0.0000

Data Index: 617074 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.7326. Min Act: -0.0000

Data Index: 1126234 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.7576. Min Act: -0.0001

Data Index: 1207608 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.7617. Min Act: -0.0000

Data Index: 438394 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.6052. Min Act: -0.0000

Data Index: 797329 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.5994. Min Act: -0.0000

Data Index: 240137 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.7089. Min Act: -0.0000

Data Index: 890575 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 3.8775. Min Range: -3.8775

Max Act: 2.6297. Min Act: -0.0000

Data Index: 15393 (C4 (Web Text))

Max Activating Token Index: 658