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

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

Neuron 1965 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.3347. Min Act: -0.0000

Data Index: 1237705 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.2967. Min Act: -0.0000

Data Index: 508387 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.3296. Min Act: -0.0000

Data Index: 613062 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.1986. Min Act: -0.0000

Data Index: 71007 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.2444. Min Act: -0.0000

Data Index: 227165 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.1637. Min Act: -0.0000

Data Index: 673424 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.1575. Min Act: -0.0000

Data Index: 147378 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.0227. Min Act: -0.0000

Data Index: 213313 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.0067. Min Act: -0.0000

Data Index: 882644 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1160042 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1073824 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.0067. Min Act: -0.0000

Data Index: 939849 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.0184. Min Act: -0.0000

Data Index: 623388 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.0535. Min Act: -0.0000

Data Index: 627026 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 1.3347. Min Range: -1.3347

Max Act: 0.9357. Min Act: -0.0000

Data Index: 1322196 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.0415. Min Act: -0.0000

Data Index: 138727 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.3347. Min Range: -1.3347

Max Act: 0.9908. Min Act: -0.0000

Data Index: 7901 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 1.3347. Min Range: -1.3347

Max Act: 0.9217. Min Act: -0.0000

Data Index: 488882 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 1.3347. Min Range: -1.3347

Max Act: 1.0416. Min Act: -0.0000

Data Index: 935444 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 1.3347. Min Range: -1.3347

Max Act: 0.9670. Min Act: -0.0000

Data Index: 539283 (C4 (Web Text))

Max Activating Token Index: 477