Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 364 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.3375. Min Act: -0.0003

Data Index: 1291107 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.3378. Min Act: -0.0003

Data Index: 218512 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2999. Min Act: -0.0003

Data Index: 550745 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2899. Min Act: -0.0003

Data Index: 1355799 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.3134. Min Act: -0.0003

Data Index: 869442 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2968. Min Act: -0.0003

Data Index: 113792 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.3105. Min Act: -0.0003

Data Index: 582899 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2860. Min Act: -0.0003

Data Index: 588299 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2861. Min Act: -0.0003

Data Index: 565045 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2713. Min Act: -0.0003

Data Index: 1233483 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2866. Min Act: -0.0003

Data Index: 698354 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2648. Min Act: -0.0003

Data Index: 805269 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2554. Min Act: -0.0003

Data Index: 641429 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2635. Min Act: -0.0003

Data Index: 576977 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2741. Min Act: -0.0003

Data Index: 80531 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2626. Min Act: -0.0003

Data Index: 292538 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2547. Min Act: -0.0003

Data Index: 1081268 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2741. Min Act: -0.0003

Data Index: 1209407 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2707. Min Act: -0.0003

Data Index: 148324 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.3378. Min Range: -0.3378

Max Act: 0.2591. Min Act: -0.0003

Data Index: 849094 (C4 (Web Text))

Max Activating Token Index: 441