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

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

Neuron 1590 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4676. Min Range: -4.4676

Max Act: 4.2329. Min Act: -0.0000

Data Index: 1337190 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 4.4676. Min Range: -4.4676

Max Act: 4.4676. Min Act: -0.0000

Data Index: 199532 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 4.4676. Min Range: -4.4676

Max Act: 4.3269. Min Act: -0.0000

Data Index: 562770 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.4174. Min Act: -0.0000

Data Index: 662990 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.0842. Min Act: -0.0000

Data Index: 1124304 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.1995. Min Act: -0.0000

Data Index: 704065 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.1578. Min Act: -0.0000

Data Index: 1202388 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.1100. Min Act: -0.0000

Data Index: 835066 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.0692. Min Act: -0.0000

Data Index: 1000089 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.0568. Min Act: -0.0000

Data Index: 1211081 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.1794. Min Act: -0.0001

Data Index: 1207845 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.0511. Min Act: -0.0000

Data Index: 800447 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.8983. Min Act: -0.0000

Data Index: 709388 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.8624. Min Act: -0.0000

Data Index: 159212 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.0042. Min Act: -0.0000

Data Index: 156189 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.9782. Min Act: -0.0000

Data Index: 948310 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.9712. Min Act: -0.0001

Data Index: 191984 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.9574. Min Act: -0.0000

Data Index: 1110513 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.8159. Min Act: -0.0000

Data Index: 560806 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.8992. Min Act: -0.0001

Data Index: 476937 (C4 (Web Text))

Max Activating Token Index: 432