Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2545 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1172029 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.5669. Min Act: -0.0000

Data Index: 374765 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4740. Min Act: -0.0000

Data Index: 928427 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.5266. Min Act: -0.0000

Data Index: 340283 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4744. Min Act: -0.0000

Data Index: 242391 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4550. Min Act: -0.0000

Data Index: 433582 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4517. Min Act: -0.0000

Data Index: 144602 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.5052. Min Act: -0.0000

Data Index: 87027 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4442. Min Act: -0.0000

Data Index: 175295 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4693. Min Act: -0.0000

Data Index: 39801 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4311. Min Act: -0.0000

Data Index: 293493 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4613. Min Act: -0.0000

Data Index: 174658 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.3934. Min Act: -0.0000

Data Index: 503451 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1131758 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4316. Min Act: -0.0000

Data Index: 618717 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.3960. Min Act: -0.0000

Data Index: 332283 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4024. Min Act: -0.0000

Data Index: 370250 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4239. Min Act: -0.0000

Data Index: 732353 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1247080 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.5669. Min Range: -0.5669

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1337624 (C4 (Web Text))

Max Activating Token Index: 444