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

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

Neuron 2078 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1884. Min Range: -3.1884

Max Act: 3.0981. Min Act: -0.0001

Data Index: 80246 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 3.1884. Min Range: -3.1884

Max Act: 3.1884. Min Act: -0.0001

Data Index: 278682 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.9436. Min Act: -0.0001

Data Index: 723908 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 3.1884. Min Range: -3.1884

Max Act: 3.0683. Min Act: -0.0001

Data Index: 129002 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.4213. Min Act: -0.0001

Data Index: 1198002 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.7781. Min Act: -0.0001

Data Index: 976467 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 3.1884. Min Range: -3.1884

Max Act: 3.0445. Min Act: -0.0001

Data Index: 1190696 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.9152. Min Act: -0.0001

Data Index: 271421 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.7435. Min Act: -0.0001

Data Index: 31009 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.8581. Min Act: -0.0001

Data Index: 1355878 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.7048. Min Act: -0.0001

Data Index: 36821 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.7302. Min Act: -0.0001

Data Index: 77548 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.6751. Min Act: -0.0001

Data Index: 1194716 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.9322. Min Act: -0.0001

Data Index: 328270 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.6444. Min Act: -0.0001

Data Index: 135892 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.5339. Min Act: -0.0001

Data Index: 762866 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.6370. Min Act: -0.0001

Data Index: 1053753 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.6444. Min Act: -0.0001

Data Index: 387993 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.7775. Min Act: -0.0001

Data Index: 530847 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 3.1884. Min Range: -3.1884

Max Act: 2.7648. Min Act: -0.0001

Data Index: 534249 (C4 (Web Text))

Max Activating Token Index: 786