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

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

Neuron 821 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: 1.7115. Min Range: -1.7115

Max Act: 1.7115. Min Act: -0.0000

Data Index: 1285100 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.5073. Min Act: -0.0001

Data Index: 512464 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.4311. Min Act: -0.0001

Data Index: 631982 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.4158. Min Act: -0.0000

Data Index: 330422 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.3262. Min Act: -0.0000

Data Index: 904118 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.2969. Min Act: -0.0000

Data Index: 45432 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.2300. Min Act: -0.0000

Data Index: 146654 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.2280. Min Act: -0.0001

Data Index: 573055 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.1935. Min Act: -0.0001

Data Index: 1007039 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.2253. Min Act: -0.0000

Data Index: 507192 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.2137. Min Act: -0.0000

Data Index: 114671 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.2060. Min Act: -0.0000

Data Index: 120900 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1177426 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.2678. Min Act: -0.0000

Data Index: 1054823 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.2224. Min Act: -0.0000

Data Index: 243292 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.1713. Min Act: -0.0000

Data Index: 1357539 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.4316. Min Act: -0.0000

Data Index: 463329 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.2536. Min Act: -0.0000

Data Index: 108603 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 1.7115. Min Range: -1.7115

Max Act: 0.8865. Min Act: -0.0000

Data Index: 101187 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.2297. Min Act: -0.0000

Data Index: 846148 (C4 (Web Text))

Max Activating Token Index: 266