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

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

Neuron 4650 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.5301. Min Act: -0.0000

Data Index: 876500 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.1477. Min Act: -0.0000

Data Index: 853611 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.1011. Min Act: -0.0000

Data Index: 1354456 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.0555. Min Act: -0.0000

Data Index: 103934 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.0164. Min Act: -0.0000

Data Index: 902934 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.9716. Min Act: -0.0000

Data Index: 820230 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.9704. Min Act: -0.0000

Data Index: 1194642 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.8161. Min Act: -0.0000

Data Index: 481177 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.7990. Min Act: -0.0000

Data Index: 708713 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.9093. Min Act: -0.0000

Data Index: 730884 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.9088. Min Act: -0.0000

Data Index: 951258 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.7189. Min Act: -0.0000

Data Index: 384832 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.7076. Min Act: -0.0000

Data Index: 869054 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.8369. Min Act: -0.0000

Data Index: 363106 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.8328. Min Act: -0.0000

Data Index: 280484 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.5390. Min Act: -0.0000

Data Index: 814259 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.9213. Min Act: -0.0000

Data Index: 5004 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.9062. Min Act: -0.0000

Data Index: 200082 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.8978. Min Act: -0.0000

Data Index: 352247 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 3.5301. Min Range: -3.5301

Max Act: 2.7601. Min Act: -0.0000

Data Index: 1104992 (C4 (Web Text))

Max Activating Token Index: 140