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

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

Neuron 3810 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: 0.5537. Min Range: -0.5537

Max Act: 0.5537. Min Act: -0.0000

Data Index: 531886 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1036253 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4970. Min Act: -0.0000

Data Index: 162044 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4693. Min Act: -0.0000

Data Index: 191643 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4683. Min Act: -0.0000

Data Index: 126051 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4813. Min Act: -0.0000

Data Index: 663610 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4284. Min Act: -0.0001

Data Index: 457532 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4148. Min Act: -0.0000

Data Index: 159512 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3921. Min Act: -0.0001

Data Index: 1206414 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1184006 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3791. Min Act: -0.0000

Data Index: 591736 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3787. Min Act: -0.0000

Data Index: 381311 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4125. Min Act: -0.0001

Data Index: 555894 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.2710. Min Act: -0.0001

Data Index: 1098939 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3385. Min Act: -0.0000

Data Index: 67254 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3162. Min Act: -0.0000

Data Index: 417910 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1220314 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3125. Min Act: -0.0001

Data Index: 1282700 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.2951. Min Act: -0.0001

Data Index: 749395 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3132. Min Act: -0.0000

Data Index: 731424 (C4 (Web Text))

Max Activating Token Index: 741