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

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

Neuron 2077 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: 1.5796. Min Range: -1.5796

Max Act: 1.5796. Min Act: -0.0001

Data Index: 152780 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.5546. Min Act: -0.0001

Data Index: 256856 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.3664. Min Act: -0.0001

Data Index: 644547 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.3410. Min Act: -0.0001

Data Index: 619455 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.3714. Min Act: -0.0001

Data Index: 510428 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.2965. Min Act: -0.0001

Data Index: 1085113 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.3386. Min Act: -0.0001

Data Index: 429770 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.2867. Min Act: -0.0001

Data Index: 234634 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.3579. Min Act: -0.0001

Data Index: 1183374 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.3264. Min Act: -0.0001

Data Index: 578399 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.3109. Min Act: -0.0001

Data Index: 1184790 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1911. Min Act: -0.0001

Data Index: 584740 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.2687. Min Act: -0.0001

Data Index: 1156989 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.2494. Min Act: -0.0001

Data Index: 354330 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1345. Min Act: -0.0001

Data Index: 17222 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.2236. Min Act: -0.0001

Data Index: 882050 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.2244. Min Act: -0.0001

Data Index: 30662 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1490. Min Act: -0.0001

Data Index: 1086702 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.1811. Min Act: -0.0001

Data Index: 238361 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 1.5796. Min Range: -1.5796

Max Act: 1.2094. Min Act: -0.0001

Data Index: 563320 (C4 (Web Text))

Max Activating Token Index: 40