Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3738 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1815. Min Act: -0.0001

Data Index: 326661 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1543. Min Act: -0.0001

Data Index: 173254 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1588. Min Act: -0.0001

Data Index: 169541 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1572. Min Act: -0.0001

Data Index: 574245 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1575. Min Act: -0.0001

Data Index: 947925 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1512. Min Act: -0.0001

Data Index: 550679 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1091625 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1439. Min Act: -0.0001

Data Index: 655603 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1356. Min Act: -0.0001

Data Index: 598668 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1463. Min Act: -0.0001

Data Index: 412943 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1380. Min Act: -0.0001

Data Index: 474615 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1293. Min Act: -0.0001

Data Index: 511496 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1356. Min Act: -0.0001

Data Index: 133281 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1302. Min Act: -0.0001

Data Index: 584052 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1153. Min Act: -0.0001

Data Index: 574347 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1212642 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1180. Min Act: -0.0001

Data Index: 953046 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1212. Min Act: -0.0001

Data Index: 45693 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1165. Min Act: -0.0000

Data Index: 45946 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1109374 (C4 (Web Text))

Max Activating Token Index: 880