Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 323 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1259. Min Act: -0.0001

Data Index: 1079381 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1653. Min Act: -0.0001

Data Index: 1174772 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1756. Min Act: -0.0001

Data Index: 426684 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1013. Min Act: -0.0001

Data Index: 179897 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1149. Min Act: -0.0001

Data Index: 795373 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0010. Min Act: -0.0001

Data Index: 275371 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0069. Min Act: -0.0001

Data Index: 447714 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0083. Min Act: -0.0001

Data Index: 363746 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9647. Min Act: -0.0001

Data Index: 738934 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9531. Min Act: -0.0001

Data Index: 419467 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9542. Min Act: -0.0001

Data Index: 376395 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9503. Min Act: -0.0001

Data Index: 461298 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9452. Min Act: -0.0001

Data Index: 920654 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9661. Min Act: -0.0001

Data Index: 201969 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.8835. Min Act: -0.0001

Data Index: 869149 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9333. Min Act: -0.0001

Data Index: 560861 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.8823. Min Act: -0.0001

Data Index: 47213 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9207. Min Act: -0.0001

Data Index: 520408 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9238. Min Act: -0.0001

Data Index: 143155 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0370. Min Act: -0.0001

Data Index: 1019811 (C4 (Web Text))

Max Activating Token Index: 921