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

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

Neuron 2156 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1493. Min Range: -3.1493

Max Act: 3.1493. Min Act: -0.0000

Data Index: 1135283 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.9604. Min Act: -0.0000

Data Index: 53915 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 3.1493. Min Range: -3.1493

Max Act: 3.0747. Min Act: -0.0000

Data Index: 792159 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.8576. Min Act: -0.0000

Data Index: 154477 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.8246. Min Act: -0.0000

Data Index: 877290 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.7741. Min Act: -0.0000

Data Index: 610208 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.5408. Min Act: -0.0000

Data Index: 531837 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.6576. Min Act: -0.0000

Data Index: 873912 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.7819. Min Act: -0.0000

Data Index: 1131334 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.6816. Min Act: -0.0000

Data Index: 123789 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.5342. Min Act: -0.0000

Data Index: 661521 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.4128. Min Act: -0.0000

Data Index: 31971 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.6288. Min Act: -0.0000

Data Index: 456326 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.5106. Min Act: -0.0000

Data Index: 1121508 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.5216. Min Act: -0.0000

Data Index: 1009670 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.4693. Min Act: -0.0000

Data Index: 1083739 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.5905. Min Act: -0.0000

Data Index: 1061954 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.3345. Min Act: -0.0000

Data Index: 522073 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.2832. Min Act: -0.0000

Data Index: 1151181 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.2674. Min Act: -0.0000

Data Index: 118548 (C4 (Web Text))

Max Activating Token Index: 489