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

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

Neuron 2705 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.9308. Min Act: -0.0001

Data Index: 244336 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.9897. Min Act: -0.0001

Data Index: 474166 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.9470. Min Act: -0.0001

Data Index: 1062822 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.9241. Min Act: -0.0001

Data Index: 145284 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.8721. Min Act: -0.0001

Data Index: 1349100 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.9435. Min Act: -0.0001

Data Index: 367751 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.9060. Min Act: -0.0001

Data Index: 32536 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.8597. Min Act: -0.0001

Data Index: 177273 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.8287. Min Act: -0.0001

Data Index: 390751 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.8476. Min Act: -0.0001

Data Index: 1040490 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.8435. Min Act: -0.0001

Data Index: 401613 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.7870. Min Act: -0.0001

Data Index: 338954 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.7615. Min Act: -0.0001

Data Index: 574152 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.7811. Min Act: -0.0001

Data Index: 129684 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.8189. Min Act: -0.0001

Data Index: 36873 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.7659. Min Act: -0.0001

Data Index: 721334 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.7638. Min Act: -0.0001

Data Index: 244157 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.7832. Min Act: -0.0001

Data Index: 935248 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.7707. Min Act: -0.0001

Data Index: 1308809 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.9897. Min Range: -0.9897

Max Act: 0.7324. Min Act: -0.0001

Data Index: 1057209 (C4 (Web Text))

Max Activating Token Index: 1010