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

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

Neuron 1385 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2144. Min Range: -2.2144

Max Act: 2.2144. Min Act: -0.0001

Data Index: 1214466 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 2.2144. Min Range: -2.2144

Max Act: 2.0313. Min Act: -0.0000

Data Index: 1146142 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.8958. Min Act: -0.0000

Data Index: 1049846 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.8556. Min Act: -0.0001

Data Index: 290576 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.8461. Min Act: -0.0001

Data Index: 622851 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.6871. Min Act: -0.0001

Data Index: 596946 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.8247. Min Act: -0.0000

Data Index: 262345 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.6766. Min Act: -0.0000

Data Index: 1125055 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.6897. Min Act: -0.0001

Data Index: 581970 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.6698. Min Act: -0.0000

Data Index: 753596 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.6037. Min Act: -0.0000

Data Index: 418350 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.6918. Min Act: -0.0000

Data Index: 23018 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.5478. Min Act: -0.0001

Data Index: 1110254 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.5920. Min Act: -0.0000

Data Index: 940031 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.6095. Min Act: -0.0000

Data Index: 404822 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.5188. Min Act: -0.0000

Data Index: 303527 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.5103. Min Act: -0.0000

Data Index: 1168663 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.5434. Min Act: -0.0001

Data Index: 894576 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.5412. Min Act: -0.0000

Data Index: 895248 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 2.2144. Min Range: -2.2144

Max Act: 1.5335. Min Act: -0.0000

Data Index: 550335 (C4 (Web Text))

Max Activating Token Index: 428