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

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

Neuron 3482 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7132. Min Range: -2.7132

Max Act: 2.7132. Min Act: -0.0000

Data Index: 19802 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 2.7132. Min Range: -2.7132

Max Act: 2.5594. Min Act: -0.0000

Data Index: 194168 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 2.7132. Min Range: -2.7132

Max Act: 2.4775. Min Act: -0.0000

Data Index: 906088 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 2.7132. Min Range: -2.7132

Max Act: 2.0822. Min Act: -0.0000

Data Index: 953640 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.7480. Min Act: -0.0000

Data Index: 496124 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.7975. Min Act: -0.0000

Data Index: 769864 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.8383. Min Act: -0.0000

Data Index: 1060781 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.9302. Min Act: -0.0000

Data Index: 872025 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.6948. Min Act: -0.0000

Data Index: 677988 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.6740. Min Act: -0.0000

Data Index: 746685 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.6502. Min Act: -0.0000

Data Index: 1278198 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.7347. Min Act: -0.0000

Data Index: 1101605 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.6877. Min Act: -0.0000

Data Index: 785860 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.6026. Min Act: -0.0000

Data Index: 1292070 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.5398. Min Act: -0.0000

Data Index: 992906 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.7104. Min Act: -0.0000

Data Index: 1216739 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.6718. Min Act: -0.0000

Data Index: 1351182 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.5678. Min Act: -0.0000

Data Index: 661638 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.6517. Min Act: -0.0000

Data Index: 620575 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 2.7132. Min Range: -2.7132

Max Act: 1.4528. Min Act: -0.0000

Data Index: 1166821 (C4 (Web Text))

Max Activating Token Index: 566