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

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

Neuron 5381 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7931. Min Act: -0.0001

Data Index: 607667 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7823. Min Act: -0.0001

Data Index: 1102279 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7508. Min Act: -0.0001

Data Index: 907636 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7495. Min Act: -0.0001

Data Index: 426208 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7460. Min Act: -0.0001

Data Index: 24188 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7253. Min Act: -0.0001

Data Index: 1239769 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7408. Min Act: -0.0001

Data Index: 858547 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7463. Min Act: -0.0001

Data Index: 437558 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7469. Min Act: -0.0001

Data Index: 81782 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7351. Min Act: -0.0001

Data Index: 170388 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7225. Min Act: -0.0001

Data Index: 1229253 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7150. Min Act: -0.0001

Data Index: 798566 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7198. Min Act: -0.0001

Data Index: 13021 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7124. Min Act: -0.0001

Data Index: 1349847 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7206. Min Act: -0.0001

Data Index: 1035878 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7361. Min Act: -0.0001

Data Index: 20130 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7299. Min Act: -0.0001

Data Index: 839564 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6952. Min Act: -0.0001

Data Index: 399597 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6977. Min Act: -0.0001

Data Index: 469305 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7280. Min Act: -0.0001

Data Index: 285279 (C4 (Web Text))

Max Activating Token Index: 703