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

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

Neuron 5685 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.6192. Min Act: -0.0000

Data Index: 564760 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.7373. Min Act: -0.0000

Data Index: 1310863 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.6534. Min Act: -0.0000

Data Index: 828995 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.6089. Min Act: -0.0000

Data Index: 861193 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.5983. Min Act: -0.0000

Data Index: 632507 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.5356. Min Act: -0.0000

Data Index: 933192 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.5315. Min Act: -0.0000

Data Index: 427287 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.5279. Min Act: -0.0000

Data Index: 217806 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.3644. Min Act: -0.0000

Data Index: 1336004 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.5095. Min Act: -0.0000

Data Index: 550256 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.3895. Min Act: -0.0000

Data Index: 1270923 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.6073. Min Act: -0.0000

Data Index: 915576 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.4662. Min Act: -0.0000

Data Index: 843295 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.3059. Min Act: -0.0000

Data Index: 412013 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.4447. Min Act: -0.0000

Data Index: 1259508 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.3426. Min Act: -0.0000

Data Index: 850905 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.4132. Min Act: -0.0000

Data Index: 72701 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.1349. Min Act: -0.0000

Data Index: 412803 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.4069. Min Act: -0.0000

Data Index: 730829 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 2.7373. Min Range: -2.7373

Max Act: 2.3831. Min Act: -0.0000

Data Index: 401270 (C4 (Web Text))

Max Activating Token Index: 59