Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2742 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1707. Min Act: -0.0001

Data Index: 36215 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1534. Min Act: -0.0001

Data Index: 353669 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1548. Min Act: -0.0001

Data Index: 187845 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1524. Min Act: -0.0001

Data Index: 657254 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1237. Min Act: -0.0001

Data Index: 927110 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1282851 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1462. Min Act: -0.0001

Data Index: 924049 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1411. Min Act: -0.0001

Data Index: 337260 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1310. Min Act: -0.0001

Data Index: 310281 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1464. Min Act: -0.0001

Data Index: 294293 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1259. Min Act: -0.0001

Data Index: 948485 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1295. Min Act: -0.0001

Data Index: 427666 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1470. Min Act: -0.0001

Data Index: 776412 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1325. Min Act: -0.0001

Data Index: 57678 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1352. Min Act: -0.0001

Data Index: 965483 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1637239 (Python Code)

Max Activating Token Index: 528

Text #16

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1255. Min Act: -0.0001

Data Index: 538324 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1345. Min Act: -0.0001

Data Index: 604245 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1234. Min Act: -0.0001

Data Index: 274602 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1237. Min Act: -0.0001

Data Index: 971314 (C4 (Web Text))

Max Activating Token Index: 932