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

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

Neuron 340 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: 6.1437. Min Range: -6.1437

Max Act: 6.1437. Min Act: -0.0000

Data Index: 281048 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 6.1437. Min Range: -6.1437

Max Act: 4.9584. Min Act: -0.0000

Data Index: 1010521 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 6.1437. Min Range: -6.1437

Max Act: 4.1788. Min Act: -0.0000

Data Index: 858990 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 6.1437. Min Range: -6.1437

Max Act: 4.1708. Min Act: -0.0000

Data Index: 213644 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 6.1437. Min Range: -6.1437

Max Act: 4.0996. Min Act: -0.0000

Data Index: 243108 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.9238. Min Act: -0.0000

Data Index: 397638 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.9773. Min Act: -0.0000

Data Index: 1031753 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.9474. Min Act: -0.0000

Data Index: 293208 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.9318. Min Act: -0.0000

Data Index: 653404 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.8792. Min Act: -0.0000

Data Index: 831883 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 6.1437. Min Range: -6.1437

Max Act: 4.0147. Min Act: -0.0000

Data Index: 272216 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 6.1437. Min Range: -6.1437

Max Act: 4.0365. Min Act: -0.0000

Data Index: 996904 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.8180. Min Act: -0.0000

Data Index: 582614 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.9522. Min Act: -0.0000

Data Index: 603687 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.7534. Min Act: -0.0000

Data Index: 347667 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.9016. Min Act: -0.0000

Data Index: 371022 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.8699. Min Act: -0.0000

Data Index: 630034 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.8702. Min Act: -0.0000

Data Index: 283826 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.8561. Min Act: -0.0000

Data Index: 1069980 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 6.1437. Min Range: -6.1437

Max Act: 3.5135. Min Act: -0.0000

Data Index: 143707 (C4 (Web Text))

Max Activating Token Index: 325