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

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

Neuron 5091 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: 2.0416. Min Range: -2.0416

Max Act: 2.0416. Min Act: -0.0000

Data Index: 898668 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.7662. Min Act: -0.0000

Data Index: 1054622 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.7673. Min Act: -0.0000

Data Index: 759421 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.5900. Min Act: -0.0000

Data Index: 1001218 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.6130. Min Act: -0.0000

Data Index: 390213 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.5188. Min Act: -0.0000

Data Index: 450296 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.3655. Min Act: -0.0000

Data Index: 908534 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.3572. Min Act: -0.0000

Data Index: 333831 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1263306 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.2548. Min Act: -0.0000

Data Index: 174566 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.2411. Min Act: -0.0000

Data Index: 721070 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.2967. Min Act: -0.0000

Data Index: 1002714 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.2874. Min Act: -0.0000

Data Index: 84148 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.3721. Min Act: -0.0000

Data Index: 1038421 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1146655 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.2107. Min Act: -0.0000

Data Index: 709232 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.1391. Min Act: -0.0000

Data Index: 759457 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.1888. Min Act: -0.0000

Data Index: 196516 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.2933. Min Act: -0.0000

Data Index: 1129342 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 2.0416. Min Range: -2.0416

Max Act: 1.2345. Min Act: -0.0000

Data Index: 1125236 (C4 (Web Text))

Max Activating Token Index: 144