Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3582 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.4922. Min Act: -0.0000

Data Index: 708278 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.4008. Min Act: -0.0000

Data Index: 836729 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.2701. Min Act: -0.0000

Data Index: 643105 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.3684. Min Act: -0.0000

Data Index: 155677 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.3015. Min Act: -0.0000

Data Index: 1015353 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.4012. Min Act: -0.0000

Data Index: 209231 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.1296. Min Act: -0.0000

Data Index: 1096920 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.0974. Min Act: -0.0000

Data Index: 989410 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.0921. Min Act: -0.0000

Data Index: 431677 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.0481. Min Act: -0.0000

Data Index: 953009 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 2.4922. Min Range: -2.4922

Max Act: 1.9222. Min Act: -0.0000

Data Index: 10298 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 2.4922. Min Range: -2.4922

Max Act: 1.9985. Min Act: -0.0000

Data Index: 284010 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.0833. Min Act: -0.0000

Data Index: 537749 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.1901. Min Act: -0.0000

Data Index: 11698 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.1774. Min Act: -0.0000

Data Index: 400447 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.0403. Min Act: -0.0000

Data Index: 1095147 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 2.4922. Min Range: -2.4922

Max Act: 1.9219. Min Act: -0.0000

Data Index: 1107257 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.0237. Min Act: -0.0000

Data Index: 555159 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.2317. Min Act: -0.0000

Data Index: 566315 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 2.4922. Min Range: -2.4922

Max Act: 2.1004. Min Act: -0.0000

Data Index: 757117 (C4 (Web Text))

Max Activating Token Index: 729