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

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

Neuron 2237 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.1063. Min Range: -2.1063

Max Act: 2.1063. Min Act: -0.0001

Data Index: 308202 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 2.1063. Min Range: -2.1063

Max Act: 2.0403. Min Act: -0.0001

Data Index: 280839 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.7898. Min Act: -0.0001

Data Index: 502226 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.8831. Min Act: -0.0001

Data Index: 309987 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.9669. Min Act: -0.0001

Data Index: 1329510 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 2.1063. Min Range: -2.1063

Max Act: 2.0709. Min Act: -0.0001

Data Index: 800279 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.7853. Min Act: -0.0001

Data Index: 1185083 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6717. Min Act: -0.0001

Data Index: 1194869 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6244. Min Act: -0.0001

Data Index: 1359835 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6064. Min Act: -0.0001

Data Index: 68406 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.5788. Min Act: -0.0001

Data Index: 990893 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6761. Min Act: -0.0001

Data Index: 636537 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6532. Min Act: -0.0001

Data Index: 1169162 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.5403. Min Act: -0.0001

Data Index: 745203 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6118. Min Act: -0.0001

Data Index: 1007607 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.4930. Min Act: -0.0001

Data Index: 417682 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.3925. Min Act: -0.0001

Data Index: 622297 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.3864. Min Act: -0.0001

Data Index: 493461 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.4586. Min Act: -0.0001

Data Index: 1101173 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.4497. Min Act: -0.0001

Data Index: 709954 (C4 (Web Text))

Max Activating Token Index: 282