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

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

Neuron 2250 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0441. Min Range: -7.0441

Max Act: 7.0441. Min Act: -0.0000

Data Index: 722045 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 7.0441. Min Range: -7.0441

Max Act: 6.4234. Min Act: -0.0000

Data Index: 1310984 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.5637. Min Act: -0.0000

Data Index: 343868 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.5588. Min Act: -0.0000

Data Index: 1236540 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.5302. Min Act: -0.0000

Data Index: 486617 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.5155. Min Act: -0.0000

Data Index: 1173130 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.2470. Min Act: -0.0000

Data Index: 1309132 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.3199. Min Act: -0.0000

Data Index: 509176 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.3306. Min Act: -0.0000

Data Index: 575080 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.1559. Min Act: -0.0000

Data Index: 1342784 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.1931. Min Act: -0.0000

Data Index: 53183 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 7.0441. Min Range: -7.0441

Max Act: 4.5820. Min Act: -0.0000

Data Index: 614707 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.0483. Min Act: -0.0000

Data Index: 190080 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.0573. Min Act: -0.0000

Data Index: 724879 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.2109. Min Act: -0.0000

Data Index: 1066694 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 7.0441. Min Range: -7.0441

Max Act: 4.9956. Min Act: -0.0000

Data Index: 482996 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.1863. Min Act: -0.0000

Data Index: 26515 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.2403. Min Act: -0.0000

Data Index: 426182 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 7.0441. Min Range: -7.0441

Max Act: 4.9946. Min Act: -0.0000

Data Index: 34897 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 7.0441. Min Range: -7.0441

Max Act: 5.1624. Min Act: -0.0000

Data Index: 1026099 (C4 (Web Text))

Max Activating Token Index: 587