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

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

Neuron 5356 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: 2.4483. Min Range: -2.4483

Max Act: 2.4483. Min Act: -0.0000

Data Index: 177215 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 2.4483. Min Range: -2.4483

Max Act: 2.3071. Min Act: -0.0000

Data Index: 770935 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 2.4483. Min Range: -2.4483

Max Act: 2.2423. Min Act: -0.0000

Data Index: 170323 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 2.4483. Min Range: -2.4483

Max Act: 2.2234. Min Act: -0.0000

Data Index: 471310 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 2.4483. Min Range: -2.4483

Max Act: 2.2440. Min Act: -0.0000

Data Index: 924651 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 2.4483. Min Range: -2.4483

Max Act: 2.1783. Min Act: -0.0000

Data Index: 564499 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 2.4483. Min Range: -2.4483

Max Act: 2.0012. Min Act: -0.0000

Data Index: 1210557 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.9648. Min Act: -0.0000

Data Index: 770776 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.9584. Min Act: -0.0000

Data Index: 109056 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.9876. Min Act: -0.0000

Data Index: 1176986 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.8556. Min Act: -0.0000

Data Index: 1256603 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.9281. Min Act: -0.0000

Data Index: 1111464 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.7940. Min Act: -0.0000

Data Index: 1233388 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.7802. Min Act: -0.0000

Data Index: 704308 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.7725. Min Act: -0.0000

Data Index: 908929 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.7455. Min Act: -0.0000

Data Index: 1339504 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.7512. Min Act: -0.0000

Data Index: 457034 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.7210. Min Act: -0.0000

Data Index: 367567 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.7214. Min Act: -0.0000

Data Index: 16601 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 2.4483. Min Range: -2.4483

Max Act: 1.7790. Min Act: -0.0000

Data Index: 951099 (C4 (Web Text))

Max Activating Token Index: 996