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

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

Neuron 197 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0780. Min Range: -2.0780

Max Act: 2.0780. Min Act: -0.0000

Data Index: 1050503 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.8628. Min Act: -0.0000

Data Index: 293774 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.8031. Min Act: -0.0000

Data Index: 1244319 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.6711. Min Act: -0.0000

Data Index: 395217 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.5941. Min Act: -0.0000

Data Index: 64658 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.5678. Min Act: -0.0000

Data Index: 297215 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.5083. Min Act: -0.0000

Data Index: 305128 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.4803. Min Act: -0.0000

Data Index: 927773 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.4370. Min Act: -0.0000

Data Index: 808247 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.4514. Min Act: -0.0000

Data Index: 705613 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.4280. Min Act: -0.0000

Data Index: 528892 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.4280. Min Act: -0.0000

Data Index: 862763 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.3754. Min Act: -0.0000

Data Index: 1183818 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.3466. Min Act: -0.0000

Data Index: 572752 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1330386 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.3320. Min Act: -0.0000

Data Index: 1045210 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.4179. Min Act: -0.0000

Data Index: 138512 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.4303. Min Act: -0.0000

Data Index: 49419 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.3565. Min Act: -0.0000

Data Index: 197236 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.2836. Min Act: -0.0000

Data Index: 36580 (C4 (Web Text))

Max Activating Token Index: 849