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

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

Neuron 5123 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: 1.4576. Min Range: -1.4576

Max Act: 1.3001. Min Act: -0.0000

Data Index: 890329 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.4576. Min Act: -0.0000

Data Index: 851276 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.1591. Min Act: -0.0000

Data Index: 209934 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.1866. Min Act: -0.0000

Data Index: 175780 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1049847 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1116059 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0950. Min Act: -0.0000

Data Index: 102503 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0583. Min Act: -0.0000

Data Index: 63205 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0921. Min Act: -0.0000

Data Index: 145458 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1109693 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0603. Min Act: -0.0000

Data Index: 883871 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.1250. Min Act: -0.0000

Data Index: 453359 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0700. Min Act: -0.0000

Data Index: 255678 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0290. Min Act: -0.0000

Data Index: 989911 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0238. Min Act: -0.0000

Data Index: 458208 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0253. Min Act: -0.0000

Data Index: 165619 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1186443 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0424. Min Act: -0.0000

Data Index: 63493 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0416. Min Act: -0.0000

Data Index: 625704 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 1.4576. Min Range: -1.4576

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1088008 (C4 (Web Text))

Max Activating Token Index: 518