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

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

Neuron 4891 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.4153. Min Act: -0.0000

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.3041. Min Act: -0.0001

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.2869. Min Act: -0.0001

Data Index: 1135148 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.9688. Min Act: -0.0001

Data Index: 1163931 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1293722 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.9452. Min Act: -0.0001

Data Index: 711417 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.9731. Min Act: -0.0001

Data Index: 1034606 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.8990. Min Act: -0.0001

Data Index: 995253 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.8899. Min Act: -0.0001

Data Index: 270999 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.9108. Min Act: -0.0001

Data Index: 601224 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.9155. Min Act: -0.0000

Data Index: 899270 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.9184. Min Act: -0.0001

Data Index: 606929 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.8183. Min Act: -0.0001

Data Index: 260773 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1060067 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.8212. Min Act: -0.0000

Data Index: 140429 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.8403. Min Act: -0.0001

Data Index: 1240073 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.8331. Min Act: -0.0001

Data Index: 316001 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.8674. Min Act: -0.0001

Data Index: 771152 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.7817. Min Act: -0.0001

Data Index: 1152713 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.8377. Min Act: -0.0001

Data Index: 1192484 (C4 (Web Text))

Max Activating Token Index: 160