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

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

Neuron 2461 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8743. Min Act: -0.0001

Data Index: 975342 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8161. Min Act: -0.0001

Data Index: 313350 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8577. Min Act: -0.0001

Data Index: 56331 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8581. Min Act: -0.0001

Data Index: 86945 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8296. Min Act: -0.0001

Data Index: 1152924 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7978. Min Act: -0.0001

Data Index: 846928 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8483. Min Act: -0.0001

Data Index: 1346309 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8114. Min Act: -0.0001

Data Index: 280418 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7589. Min Act: -0.0001

Data Index: 422039 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7842. Min Act: -0.0001

Data Index: 412371 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7903. Min Act: -0.0001

Data Index: 1123728 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7445. Min Act: -0.0001

Data Index: 479016 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7567. Min Act: -0.0001

Data Index: 906133 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7924. Min Act: -0.0001

Data Index: 1122082 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7020. Min Act: -0.0001

Data Index: 391368 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7164. Min Act: -0.0001

Data Index: 854227 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7300. Min Act: -0.0001

Data Index: 265580 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7332. Min Act: -0.0001

Data Index: 725521 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6704. Min Act: -0.0001

Data Index: 225010 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7439. Min Act: -0.0001

Data Index: 1006103 (C4 (Web Text))

Max Activating Token Index: 782