Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 268 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.5359. Min Act: -0.0001

Data Index: 313849 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.5005. Min Act: -0.0001

Data Index: 229362 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.5329. Min Act: -0.0001

Data Index: 629060 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4621. Min Act: -0.0001

Data Index: 183331 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4613. Min Act: -0.0001

Data Index: 1550724 (Python Code)

Max Activating Token Index: 168

Text #5

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4448. Min Act: -0.0001

Data Index: 283049 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4787. Min Act: -0.0001

Data Index: 457506 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4327. Min Act: -0.0001

Data Index: 1044831 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1485474 (Python Code)

Max Activating Token Index: 312

Text #9

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4190. Min Act: -0.0001

Data Index: 1430592 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4169. Min Act: -0.0001

Data Index: 1099902 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4323. Min Act: -0.0001

Data Index: 551105 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4174. Min Act: -0.0001

Data Index: 234690 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4136. Min Act: -0.0001

Data Index: 822746 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4057. Min Act: -0.0001

Data Index: 76086 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3980. Min Act: -0.0001

Data Index: 1317277 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3717. Min Act: -0.0001

Data Index: 1639652 (Python Code)

Max Activating Token Index: 880

Text #17

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3730. Min Act: -0.0001

Data Index: 121711 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3885. Min Act: -0.0001

Data Index: 668231 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4302. Min Act: -0.0001

Data Index: 1579837 (Python Code)

Max Activating Token Index: 357