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

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

Neuron 4212 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4595. Min Range: -4.4595

Max Act: 4.4595. Min Act: -0.0000

Data Index: 333786 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 4.4595. Min Range: -4.4595

Max Act: 4.2358. Min Act: 0.0000

Data Index: 510394 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 4.4595. Min Range: -4.4595

Max Act: 4.2906. Min Act: -0.0000

Data Index: 533153 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.4255. Min Act: 0.0000

Data Index: 319421 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.1562. Min Act: -0.0000

Data Index: 1120412 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.2064. Min Act: -0.0000

Data Index: 826701 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.2101. Min Act: 0.0000

Data Index: 411925 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.3546. Min Act: 0.0000

Data Index: 1318133 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.1858. Min Act: 0.0000

Data Index: 151675 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.1703. Min Act: -0.0000

Data Index: 1239782 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.3815. Min Act: 0.0001

Data Index: 1156659 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.2850. Min Act: 0.0001

Data Index: 72850 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.0725. Min Act: -0.0000

Data Index: 770664 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 4.4595. Min Range: -4.4595

Max Act: 2.9259. Min Act: -0.0000

Data Index: 747298 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.0376. Min Act: -0.0000

Data Index: 1298374 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 4.4595. Min Range: -4.4595

Max Act: 3.0059. Min Act: 0.0000

Data Index: 3825 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 4.4595. Min Range: -4.4595

Max Act: 2.8398. Min Act: 0.0000

Data Index: 277683 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 4.4595. Min Range: -4.4595

Max Act: 2.8183. Min Act: -0.0000

Data Index: 801801 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 4.4595. Min Range: -4.4595

Max Act: 2.9688. Min Act: -0.0000

Data Index: 925954 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 4.4595. Min Range: -4.4595

Max Act: 2.9443. Min Act: 0.0000

Data Index: 834211 (C4 (Web Text))

Max Activating Token Index: 97