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

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

Neuron 2104 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4766. Min Act: -0.0001

Data Index: 427814 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4540. Min Act: -0.0001

Data Index: 1030249 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4513. Min Act: -0.0001

Data Index: 301572 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4515. Min Act: -0.0001

Data Index: 789568 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4312. Min Act: -0.0001

Data Index: 992115 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4554. Min Act: -0.0001

Data Index: 1058146 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4390. Min Act: -0.0001

Data Index: 97633 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4479. Min Act: -0.0001

Data Index: 323816 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4226. Min Act: -0.0001

Data Index: 632698 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4253. Min Act: -0.0001

Data Index: 1082210 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4143. Min Act: -0.0001

Data Index: 236653 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4033. Min Act: -0.0000

Data Index: 746633 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4163. Min Act: -0.0001

Data Index: 898337 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3730. Min Act: -0.0001

Data Index: 59391 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3714. Min Act: -0.0001

Data Index: 993408 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3112. Min Act: -0.0001

Data Index: 544367 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3153. Min Act: -0.0000

Data Index: 488068 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3138. Min Act: -0.0001

Data Index: 921705 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3093. Min Act: -0.0001

Data Index: 444673 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1236741 (C4 (Web Text))

Max Activating Token Index: 227