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

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

Neuron 3669 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2939. Min Range: -2.2939

Max Act: 2.2939. Min Act: -0.0000

Data Index: 1025046 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 2.2939. Min Range: -2.2939

Max Act: 2.0828. Min Act: -0.0000

Data Index: 475339 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 2.2939. Min Range: -2.2939

Max Act: 2.1583. Min Act: -0.0000

Data Index: 625202 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.9468. Min Act: -0.0000

Data Index: 1146239 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.7765. Min Act: -0.0000

Data Index: 619620 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.7582. Min Act: -0.0000

Data Index: 637758 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.8013. Min Act: -0.0000

Data Index: 1008520 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.8623. Min Act: -0.0000

Data Index: 565389 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.5913. Min Act: -0.0000

Data Index: 1262124 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.7413. Min Act: -0.0000

Data Index: 841649 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.6411. Min Act: -0.0000

Data Index: 897730 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.6429. Min Act: -0.0000

Data Index: 1166480 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.5270. Min Act: -0.0000

Data Index: 601357 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.8280. Min Act: -0.0000

Data Index: 1255248 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.5398. Min Act: -0.0000

Data Index: 1223042 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.7214. Min Act: -0.0000

Data Index: 1225506 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.8110. Min Act: -0.0000

Data Index: 717380 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.5742. Min Act: -0.0000

Data Index: 454341 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.5466. Min Act: -0.0000

Data Index: 972383 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 2.2939. Min Range: -2.2939

Max Act: 1.6313. Min Act: -0.0000

Data Index: 1109934 (C4 (Web Text))

Max Activating Token Index: 292