Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1158 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.8352. Min Act: -0.0001

Data Index: 143581 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7584. Min Act: -0.0001

Data Index: 3018 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7763. Min Act: -0.0001

Data Index: 1022335 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7646. Min Act: -0.0001

Data Index: 91612 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7553. Min Act: -0.0001

Data Index: 149054 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7294. Min Act: -0.0001

Data Index: 608767 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7079. Min Act: -0.0001

Data Index: 400381 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7170. Min Act: -0.0001

Data Index: 196871 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6933. Min Act: -0.0000

Data Index: 733550 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6853. Min Act: -0.0001

Data Index: 628307 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6649. Min Act: -0.0001

Data Index: 396416 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6865. Min Act: -0.0001

Data Index: 607853 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6716. Min Act: -0.0001

Data Index: 1204911 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6654. Min Act: -0.0001

Data Index: 695424 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6966. Min Act: -0.0001

Data Index: 690038 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6279. Min Act: -0.0001

Data Index: 580261 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6412. Min Act: -0.0001

Data Index: 1120659 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6111. Min Act: -0.0001

Data Index: 916949 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6585. Min Act: -0.0001

Data Index: 1248147 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5846. Min Act: -0.0001

Data Index: 1163389 (C4 (Web Text))

Max Activating Token Index: 952