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

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

Neuron 1747 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: 1.7154. Min Range: -1.7154

Max Act: 1.6496. Min Act: -0.0000

Data Index: 1169940 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.7154. Min Act: -0.0000

Data Index: 774305 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.7021. Min Act: -0.0000

Data Index: 736116 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.5513. Min Act: -0.0000

Data Index: 963490 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.3548. Min Act: -0.0000

Data Index: 447225 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.4531. Min Act: -0.0000

Data Index: 1313198 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.3440. Min Act: -0.0000

Data Index: 714417 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.3365. Min Act: -0.0000

Data Index: 1468118 (Python Code)

Max Activating Token Index: 347

Text #8

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.2764. Min Act: -0.0000

Data Index: 792316 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.3145. Min Act: -0.0000

Data Index: 137276 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.2175. Min Act: -0.0000

Data Index: 1461770 (Python Code)

Max Activating Token Index: 885

Text #11

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.2331. Min Act: -0.0000

Data Index: 1580400 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1645455 (Python Code)

Max Activating Token Index: 140

Text #13

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1492676 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1234. Min Act: -0.0000

Data Index: 1501930 (Python Code)

Max Activating Token Index: 196

Text #15

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1096. Min Act: -0.0000

Data Index: 706991 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1632. Min Act: -0.0000

Data Index: 1599841 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.0529. Min Act: -0.0000

Data Index: 1361945 (Python Code)

Max Activating Token Index: 126

Text #18

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1511. Min Act: -0.0000

Data Index: 784318 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1480795 (Python Code)

Max Activating Token Index: 535