Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 156 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1092310 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0523. Min Act: -0.0003

Data Index: 589056 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0521. Min Act: -0.0003

Data Index: 367100 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1270188 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0461. Min Act: -0.0004

Data Index: 704121 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0474. Min Act: -0.0003

Data Index: 199778 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1229696 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0453. Min Act: -0.0003

Data Index: 369421 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0430. Min Act: -0.0003

Data Index: 588617 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1213340 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0428. Min Act: -0.0003

Data Index: 514538 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0452. Min Act: -0.0003

Data Index: 522066 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1236805 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1025149 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1206066 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0411. Min Act: -0.0004

Data Index: 311120 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0371. Min Act: -0.0003

Data Index: 330926 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0408. Min Act: -0.0004

Data Index: 1144707 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1142850 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1188602 (C4 (Web Text))

Max Activating Token Index: 157