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

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

Neuron 527 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: 1.1763. Min Range: -1.1763

Max Act: 1.1574. Min Act: -0.0001

Data Index: 802936 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0759. Min Act: -0.0001

Data Index: 1039195 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0983. Min Act: -0.0001

Data Index: 111049 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.1763. Min Act: -0.0001

Data Index: 934854 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0598. Min Act: -0.0001

Data Index: 1253637 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0140. Min Act: -0.0001

Data Index: 70293 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0081. Min Act: -0.0001

Data Index: 1153560 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0790. Min Act: -0.0001

Data Index: 889186 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0288. Min Act: -0.0001

Data Index: 1001614 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0182. Min Act: -0.0001

Data Index: 691479 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0174. Min Act: -0.0001

Data Index: 390971 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9698. Min Act: -0.0001

Data Index: 865880 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0223. Min Act: -0.0001

Data Index: 965093 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9985. Min Act: -0.0001

Data Index: 149652 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9548. Min Act: -0.0001

Data Index: 836087 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9669. Min Act: -0.0001

Data Index: 1308064 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9638. Min Act: -0.0001

Data Index: 162664 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9379. Min Act: -0.0001

Data Index: 1042351 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9622. Min Act: -0.0001

Data Index: 551687 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9239. Min Act: -0.0001

Data Index: 1048338 (C4 (Web Text))

Max Activating Token Index: 848