Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2422 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.4135. Min Act: -0.0000

Data Index: 831086 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3463. Min Act: -0.0000

Data Index: 473104 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3214. Min Act: -0.0000

Data Index: 290184 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3462. Min Act: -0.0000

Data Index: 356882 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3434. Min Act: -0.0000

Data Index: 491574 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3336. Min Act: -0.0000

Data Index: 576708 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3210. Min Act: -0.0000

Data Index: 828220 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3317. Min Act: -0.0000

Data Index: 193653 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3206. Min Act: -0.0000

Data Index: 625907 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3165. Min Act: -0.0000

Data Index: 896020 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.2936. Min Act: -0.0000

Data Index: 328801 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.2783. Min Act: -0.0000

Data Index: 768119 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.2773. Min Act: -0.0000

Data Index: 378800 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1346460 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1116475 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.2818. Min Act: -0.0000

Data Index: 79070 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.2877. Min Act: -0.0000

Data Index: 219719 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1235152 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.2798. Min Act: -0.0000

Data Index: 459196 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.2680. Min Act: -0.0000

Data Index: 769259 (C4 (Web Text))

Max Activating Token Index: 997