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

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

Neuron 3122 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.8263. Min Act: -0.0001

Data Index: 155048 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.0568. Min Act: -0.0001

Data Index: 741339 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.9592. Min Act: -0.0001

Data Index: 905212 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.2929. Min Act: -0.0000

Data Index: 938988 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.1130. Min Act: -0.0000

Data Index: 55521 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.1074. Min Act: -0.0000

Data Index: 982190 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.0584. Min Act: -0.0000

Data Index: 1285855 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.8050. Min Act: -0.0000

Data Index: 720264 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.9246. Min Act: -0.0000

Data Index: 699441 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.5225. Min Act: -0.0000

Data Index: 1107937 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.9028. Min Act: -0.0000

Data Index: 1330958 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.7593. Min Act: -0.0000

Data Index: 159792 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.0235. Min Act: -0.0000

Data Index: 1091428 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.7033. Min Act: -0.0000

Data Index: 864459 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.9694. Min Act: -0.0001

Data Index: 869729 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.7822. Min Act: -0.0000

Data Index: 271730 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.3533. Min Act: -0.0000

Data Index: 1323374 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.3626. Min Act: -0.0001

Data Index: 840458 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.3299. Min Act: -0.0001

Data Index: 334137 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 3.8263. Min Range: -3.8263

Max Act: 2.6547. Min Act: -0.0000

Data Index: 767659 (C4 (Web Text))

Max Activating Token Index: 175