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

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

Neuron 657 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: 1.1961. Min Range: -1.1961

Max Act: 1.1961. Min Act: -0.0001

Data Index: 92911 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 1.1961. Min Range: -1.1961

Max Act: 1.1475. Min Act: -0.0001

Data Index: 1169774 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9305. Min Act: -0.0001

Data Index: 1158301 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8779. Min Act: -0.0001

Data Index: 732056 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8463. Min Act: -0.0001

Data Index: 161968 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8570. Min Act: -0.0001

Data Index: 1021311 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8539. Min Act: -0.0001

Data Index: 151316 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8084. Min Act: -0.0001

Data Index: 37228 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.6817. Min Act: -0.0001

Data Index: 1044335 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7895. Min Act: -0.0001

Data Index: 707142 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7819. Min Act: -0.0001

Data Index: 375330 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7719. Min Act: -0.0001

Data Index: 335764 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7908. Min Act: -0.0001

Data Index: 364677 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7168. Min Act: -0.0001

Data Index: 131740 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8172. Min Act: -0.0001

Data Index: 552285 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7367. Min Act: -0.0001

Data Index: 158880 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7308. Min Act: -0.0001

Data Index: 1196628 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7471. Min Act: -0.0001

Data Index: 839775 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7501. Min Act: -0.0001

Data Index: 1079359 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7436. Min Act: -0.0001

Data Index: 555711 (C4 (Web Text))

Max Activating Token Index: 357