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

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

Neuron 1617 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7270. Min Act: -0.0001

Data Index: 1230830 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.8314. Min Act: -0.0001

Data Index: 430391 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.3423. Min Act: -0.0000

Data Index: 446911 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.1152. Min Act: -0.0001

Data Index: 428266 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.1056. Min Act: -0.0000

Data Index: 510721 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.0656. Min Act: -0.0000

Data Index: 314277 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.9439. Min Act: -0.0001

Data Index: 1116543 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.0039. Min Act: -0.0000

Data Index: 58407 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.9783. Min Act: -0.0000

Data Index: 1316825 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.7183. Min Act: -0.0001

Data Index: 63406 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.9602. Min Act: -0.0000

Data Index: 1249960 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.9896. Min Act: -0.0000

Data Index: 498145 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.8784. Min Act: -0.0001

Data Index: 1240483 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1191716 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.8405. Min Act: -0.0000

Data Index: 981937 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.8249. Min Act: -0.0001

Data Index: 412924 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.8277. Min Act: -0.0000

Data Index: 762899 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.8154. Min Act: -0.0000

Data Index: 1007857 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.7069. Min Act: -0.0001

Data Index: 354441 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 2.8314. Min Range: -2.8314

Max Act: 1.8972. Min Act: -0.0000

Data Index: 233848 (C4 (Web Text))

Max Activating Token Index: 224