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

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

Neuron 636 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.7030. Min Act: -0.0000

Data Index: 940764 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6623. Min Act: -0.0000

Data Index: 46168 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6162. Min Act: -0.0000

Data Index: 15504 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5901. Min Act: -0.0000

Data Index: 291222 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5887. Min Act: 0.0001

Data Index: 112824 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5592. Min Act: -0.0000

Data Index: 619632 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5749. Min Act: 0.0001

Data Index: 32271 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5552. Min Act: -0.0000

Data Index: 499416 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1126027 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5757. Min Act: 0.0000

Data Index: 1314553 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1298591 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1164562 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5689. Min Act: -0.0000

Data Index: 230805 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5256. Min Act: -0.0000

Data Index: 563414 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5158. Min Act: -0.0000

Data Index: 962223 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5325. Min Act: -0.0000

Data Index: 192368 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5130. Min Act: -0.0000

Data Index: 847917 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5142. Min Act: -0.0000

Data Index: 775278 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5101. Min Act: -0.0000

Data Index: 310642 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5409. Min Act: -0.0000

Data Index: 359924 (C4 (Web Text))

Max Activating Token Index: 893