Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2017 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0747. Min Range: -1.0747

Max Act: 1.0158. Min Act: -0.0001

Data Index: 1033287 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.0747. Min Range: -1.0747

Max Act: 1.0747. Min Act: -0.0001

Data Index: 1188416 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.9921. Min Act: -0.0001

Data Index: 267529 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.9549. Min Act: -0.0001

Data Index: 491830 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.9535. Min Act: -0.0001

Data Index: 248020 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.9110. Min Act: -0.0001

Data Index: 582543 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.9021. Min Act: -0.0001

Data Index: 1190655 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.9221. Min Act: -0.0001

Data Index: 842778 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.9139. Min Act: -0.0001

Data Index: 1287398 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.9753. Min Act: -0.0001

Data Index: 475962 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.8619. Min Act: -0.0001

Data Index: 855444 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.8644. Min Act: -0.0001

Data Index: 1343873 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.8645. Min Act: -0.0001

Data Index: 1246178 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.9082. Min Act: -0.0001

Data Index: 267564 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.8281. Min Act: -0.0001

Data Index: 180784 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.8170. Min Act: -0.0001

Data Index: 867838 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.8679. Min Act: -0.0001

Data Index: 545569 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.7947. Min Act: -0.0001

Data Index: 1258237 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.7941. Min Act: -0.0001

Data Index: 756934 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 1.0747. Min Range: -1.0747

Max Act: 0.8359. Min Act: -0.0001

Data Index: 712465 (C4 (Web Text))

Max Activating Token Index: 976