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

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

Neuron 2053 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8933. Min Act: -0.0001

Data Index: 1008540 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.1034. Min Range: -1.1034

Max Act: 1.1034. Min Act: -0.0001

Data Index: 822164 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.1034. Min Range: -1.1034

Max Act: 1.0508. Min Act: -0.0001

Data Index: 1055724 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9988. Min Act: -0.0001

Data Index: 720486 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9324. Min Act: -0.0001

Data Index: 11542 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8286. Min Act: -0.0001

Data Index: 1159825 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8353. Min Act: -0.0001

Data Index: 707428 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8582. Min Act: -0.0001

Data Index: 202004 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7943. Min Act: -0.0001

Data Index: 273655 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9259. Min Act: -0.0001

Data Index: 795580 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8249. Min Act: -0.0001

Data Index: 239786 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8059. Min Act: -0.0001

Data Index: 89485 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8523. Min Act: -0.0001

Data Index: 1220633 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8772. Min Act: -0.0001

Data Index: 710412 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8469. Min Act: -0.0001

Data Index: 399536 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8425. Min Act: -0.0001

Data Index: 550468 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8459. Min Act: -0.0001

Data Index: 931920 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7823. Min Act: -0.0001

Data Index: 582883 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7801. Min Act: -0.0001

Data Index: 1246493 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8304. Min Act: -0.0001

Data Index: 129808 (C4 (Web Text))

Max Activating Token Index: 447