Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5032 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4665. Min Range: -2.4665

Max Act: 2.4665. Min Act: -0.0000

Data Index: 377175 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 2.4665. Min Range: -2.4665

Max Act: 2.1983. Min Act: -0.0000

Data Index: 1173531 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 2.4665. Min Range: -2.4665

Max Act: 2.3004. Min Act: -0.0000

Data Index: 123727 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 2.4665. Min Range: -2.4665

Max Act: 2.1569. Min Act: -0.0000

Data Index: 813960 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.9347. Min Act: -0.0000

Data Index: 1170056 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.9403. Min Act: -0.0000

Data Index: 971056 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8730. Min Act: -0.0000

Data Index: 301835 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 2.4665. Min Range: -2.4665

Max Act: 2.1630. Min Act: -0.0000

Data Index: 760697 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.9856. Min Act: -0.0000

Data Index: 797367 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8498. Min Act: -0.0000

Data Index: 525461 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.9413. Min Act: -0.0000

Data Index: 737 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8170. Min Act: -0.0000

Data Index: 391813 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.7875. Min Act: -0.0000

Data Index: 290199 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.7808. Min Act: -0.0000

Data Index: 588214 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.6645. Min Act: -0.0000

Data Index: 1207374 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8363. Min Act: -0.0000

Data Index: 340811 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.7295. Min Act: -0.0000

Data Index: 88121 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1256053 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.6463. Min Act: -0.0000

Data Index: 882395 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.7233. Min Act: -0.0000

Data Index: 331266 (C4 (Web Text))

Max Activating Token Index: 593