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

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

Neuron 4010 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.8225. Min Act: -0.0000

Data Index: 306055 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.5964. Min Act: -0.0000

Data Index: 859735 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.4484. Min Act: -0.0000

Data Index: 278979 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.4206. Min Act: -0.0000

Data Index: 307556 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.2894. Min Act: -0.0000

Data Index: 306777 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.4418. Min Act: -0.0000

Data Index: 66224 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.3457. Min Act: -0.0000

Data Index: 1026302 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.2630. Min Act: -0.0000

Data Index: 806310 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1018727 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.3887. Min Act: -0.0000

Data Index: 406479 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.2947. Min Act: -0.0000

Data Index: 219398 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.2248. Min Act: -0.0000

Data Index: 504279 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.3502. Min Act: -0.0000

Data Index: 527606 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.2172. Min Act: -0.0000

Data Index: 1261267 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.1999. Min Act: -0.0000

Data Index: 1252752 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.2785. Min Act: -0.0000

Data Index: 1035390 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.2715. Min Act: -0.0000

Data Index: 654390 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.2583. Min Act: -0.0000

Data Index: 325638 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.2597. Min Act: -0.0000

Data Index: 678523 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.2301. Min Act: -0.0000

Data Index: 217865 (C4 (Web Text))

Max Activating Token Index: 872