Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1316 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1028174 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1183905 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0585. Min Act: -0.0003

Data Index: 881018 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0576. Min Act: -0.0003

Data Index: 703061 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0567. Min Act: -0.0003

Data Index: 514878 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0526. Min Act: -0.0004

Data Index: 454374 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0529. Min Act: -0.0003

Data Index: 786200 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0514. Min Act: -0.0004

Data Index: 310670 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0521. Min Act: -0.0003

Data Index: 84072 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0511. Min Act: -0.0003

Data Index: 62414 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0513. Min Act: -0.0003

Data Index: 870685 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0514. Min Act: -0.0003

Data Index: 532151 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0510. Min Act: -0.0003

Data Index: 105674 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1068623 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0502. Min Act: -0.0003

Data Index: 190001 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1104358 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0506. Min Act: -0.0004

Data Index: 1166755 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0518. Min Act: -0.0003

Data Index: 992302 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0507. Min Act: -0.0004

Data Index: 805912 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0511. Min Act: -0.0003

Data Index: 63985 (C4 (Web Text))

Max Activating Token Index: 37