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

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

Neuron 1105 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5792. Min Act: -0.0000

Data Index: 303021 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5757. Min Act: -0.0000

Data Index: 555151 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1275707 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1215021 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4594. Min Act: -0.0000

Data Index: 225037 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1164698 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1270174 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4485. Min Act: -0.0000

Data Index: 940780 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4325. Min Act: -0.0001

Data Index: 24600 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4509. Min Act: -0.0000

Data Index: 984394 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1201787 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4074. Min Act: -0.0001

Data Index: 827001 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4320. Min Act: -0.0000

Data Index: 314283 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4054. Min Act: -0.0000

Data Index: 940795 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4154. Min Act: -0.0000

Data Index: 921508 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4086. Min Act: -0.0000

Data Index: 658205 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4042. Min Act: -0.0001

Data Index: 1345545 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1196195 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1199162 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.3841. Min Act: -0.0001

Data Index: 239978 (C4 (Web Text))

Max Activating Token Index: 283