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

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

Neuron 3218 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.2253. Min Act: -0.0000

Data Index: 934549 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1260836 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1111720 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8731. Min Act: -0.0000

Data Index: 883215 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8201. Min Act: -0.0000

Data Index: 510368 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8128. Min Act: -0.0000

Data Index: 918261 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8145. Min Act: -0.0000

Data Index: 817634 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.8007. Min Act: -0.0000

Data Index: 146930 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1270547 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7856. Min Act: -0.0000

Data Index: 455842 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1313603 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7161. Min Act: -0.0000

Data Index: 206486 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7511. Min Act: -0.0000

Data Index: 51176 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7370. Min Act: -0.0000

Data Index: 892397 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.6945. Min Act: -0.0000

Data Index: 745116 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1040779 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7205. Min Act: -0.0000

Data Index: 588103 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7179. Min Act: -0.0000

Data Index: 55633 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.6731. Min Act: -0.0000

Data Index: 585850 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.7164. Min Act: -0.0000

Data Index: 785624 (C4 (Web Text))

Max Activating Token Index: 310