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

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

Neuron 14 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2425. Min Act: -0.0001

Data Index: 684216 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2287. Min Act: -0.0001

Data Index: 392224 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2358. Min Act: -0.0001

Data Index: 467062 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2272. Min Act: -0.0001

Data Index: 934177 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2017. Min Act: -0.0001

Data Index: 1127789 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1937. Min Act: -0.0001

Data Index: 660294 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2144. Min Act: -0.0001

Data Index: 1018183 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2044. Min Act: -0.0001

Data Index: 1122807 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1980. Min Act: -0.0001

Data Index: 867005 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2028. Min Act: -0.0001

Data Index: 1203491 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1992. Min Act: -0.0001

Data Index: 790696 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1233584 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1806. Min Act: -0.0001

Data Index: 310557 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1910. Min Act: -0.0001

Data Index: 733672 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1076563 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1780. Min Act: -0.0001

Data Index: 139291 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2030. Min Act: -0.0001

Data Index: 396243 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1282254 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1833. Min Act: -0.0001

Data Index: 481885 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1302457 (C4 (Web Text))

Max Activating Token Index: 670