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

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

Neuron 4501 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.8217. Min Act: -0.0001

Data Index: 1323770 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6579. Min Act: -0.0001

Data Index: 978632 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5740. Min Act: -0.0001

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6161. Min Act: -0.0001

Data Index: 1281786 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6346. Min Act: -0.0001

Data Index: 1141052 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6184. Min Act: -0.0001

Data Index: 725436 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6004. Min Act: -0.0001

Data Index: 200752 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5355. Min Act: -0.0001

Data Index: 680143 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5759. Min Act: -0.0001

Data Index: 80097 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5307. Min Act: -0.0001

Data Index: 1123786 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5380. Min Act: -0.0001

Data Index: 95480 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5228. Min Act: -0.0001

Data Index: 289412 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5513. Min Act: -0.0001

Data Index: 6804 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4858. Min Act: -0.0001

Data Index: 13724 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5058. Min Act: -0.0001

Data Index: 875849 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4651. Min Act: -0.0001

Data Index: 604117 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5321. Min Act: -0.0001

Data Index: 309974 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4427. Min Act: -0.0001

Data Index: 963954 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4905. Min Act: -0.0001

Data Index: 207482 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5150. Min Act: -0.0001

Data Index: 885560 (C4 (Web Text))

Max Activating Token Index: 149