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

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

Neuron 551 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6075. Min Range: -3.6075

Max Act: 3.6075. Min Act: -0.0002

Data Index: 1233116 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.3790. Min Act: -0.0002

Data Index: 716818 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 3.6075. Min Range: -3.6075

Max Act: 3.0728. Min Act: -0.0002

Data Index: 73350 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 3.6075. Min Range: -3.6075

Max Act: 3.1890. Min Act: -0.0002

Data Index: 1311325 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.9556. Min Act: -0.0002

Data Index: 309011 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.9933. Min Act: -0.0002

Data Index: 1339668 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.8515. Min Act: -0.0002

Data Index: 910993 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.4268. Min Act: -0.0002

Data Index: 219957 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.4778. Min Act: -0.0002

Data Index: 1280761 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.7689. Min Act: -0.0002

Data Index: 974960 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.8978. Min Act: -0.0002

Data Index: 645286 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 3.6075. Min Range: -3.6075

Max Act: 1.9965. Min Act: -0.0002

Data Index: 354008 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.6149. Min Act: -0.0002

Data Index: 748265 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.6244. Min Act: -0.0002

Data Index: 74609 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.3694. Min Act: -0.0002

Data Index: 914233 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.3465. Min Act: -0.0001

Data Index: 1215358 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.5855. Min Act: -0.0002

Data Index: 775641 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.6337. Min Act: -0.0002

Data Index: 293369 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.5247. Min Act: -0.0002

Data Index: 324573 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 3.6075. Min Range: -3.6075

Max Act: 2.4956. Min Act: -0.0002

Data Index: 1213167 (C4 (Web Text))

Max Activating Token Index: 482