Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1968 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.5129. Min Act: -0.0001

Data Index: 1343053 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.1287. Min Act: -0.0001

Data Index: 547188 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.1069. Min Act: -0.0001

Data Index: 491379 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8702. Min Act: -0.0001

Data Index: 611354 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.0036. Min Act: -0.0001

Data Index: 8714 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.9176. Min Act: -0.0001

Data Index: 290250 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8136. Min Act: -0.0001

Data Index: 367769 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7706. Min Act: -0.0001

Data Index: 362738 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.9229. Min Act: -0.0001

Data Index: 297398 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.9344. Min Act: -0.0001

Data Index: 90509 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8526. Min Act: -0.0001

Data Index: 183178 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.9715. Min Act: -0.0001

Data Index: 1109043 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8105. Min Act: -0.0001

Data Index: 358578 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8275. Min Act: -0.0001

Data Index: 287083 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8879. Min Act: -0.0001

Data Index: 524941 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8435. Min Act: -0.0001

Data Index: 3448 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7731. Min Act: -0.0001

Data Index: 988976 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7924. Min Act: -0.0001

Data Index: 1278176 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7693. Min Act: -0.0001

Data Index: 1070506 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8419. Min Act: -0.0001

Data Index: 893071 (C4 (Web Text))

Max Activating Token Index: 252