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

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

Neuron 2801 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.8308. Min Act: -0.0000

Data Index: 624894 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7312. Min Act: -0.0000

Data Index: 642921 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1079176 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1194511 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.5981. Min Act: -0.0000

Data Index: 618240 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.5596. Min Act: -0.0000

Data Index: 606648 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.5575. Min Act: -0.0000

Data Index: 4685 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1093220 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1122708 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.5172. Min Act: -0.0000

Data Index: 192589 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.5335. Min Act: -0.0000

Data Index: 437203 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.5095. Min Act: -0.0000

Data Index: 481059 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.5291. Min Act: -0.0000

Data Index: 158655 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.4798. Min Act: -0.0000

Data Index: 211647 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.5448. Min Act: -0.0000

Data Index: 78012 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.4951. Min Act: -0.0000

Data Index: 17288 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.4842. Min Act: -0.0000

Data Index: 754237 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1038052 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.4834. Min Act: -0.0000

Data Index: 178998 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.4855. Min Act: -0.0000

Data Index: 896056 (C4 (Web Text))

Max Activating Token Index: 812