Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 757 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.6115. Min Act: -0.0001

Data Index: 1482335 (Python Code)

Max Activating Token Index: 54

Text #1

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.3232. Min Act: -0.0001

Data Index: 1349694 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.2525. Min Act: -0.0001

Data Index: 1542100 (Python Code)

Max Activating Token Index: 950

Text #3

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.2455. Min Act: -0.0001

Data Index: 166568 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1572. Min Act: -0.0001

Data Index: 807213 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1726. Min Act: -0.0001

Data Index: 824312 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1547. Min Act: -0.0001

Data Index: 776336 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1741. Min Act: -0.0001

Data Index: 497621 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1034. Min Act: -0.0001

Data Index: 216005 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1231. Min Act: -0.0001

Data Index: 1284984 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1103. Min Act: -0.0001

Data Index: 1191891 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0734. Min Act: -0.0001

Data Index: 288957 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0756. Min Act: -0.0001

Data Index: 1536334 (Python Code)

Max Activating Token Index: 176

Text #13

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0296. Min Act: -0.0001

Data Index: 1240881 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0353. Min Act: -0.0001

Data Index: 129840 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0419. Min Act: -0.0001

Data Index: 649092 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0333. Min Act: -0.0001

Data Index: 324273 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0171. Min Act: -0.0001

Data Index: 1622939 (Python Code)

Max Activating Token Index: 154

Text #18

Max Range: 1.6115. Min Range: -1.6115

Max Act: 0.9822. Min Act: -0.0001

Data Index: 607689 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0321. Min Act: -0.0001

Data Index: 555021 (C4 (Web Text))

Max Activating Token Index: 661