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

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

Neuron 2768 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8132. Min Range: -7.8132

Max Act: 7.8132. Min Act: -0.0000

Data Index: 594505 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 7.8132. Min Range: -7.8132

Max Act: 6.6791. Min Act: -0.0000

Data Index: 922339 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 7.8132. Min Range: -7.8132

Max Act: 6.3885. Min Act: -0.0000

Data Index: 426726 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 7.8132. Min Range: -7.8132

Max Act: 6.3394. Min Act: -0.0000

Data Index: 1036836 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 7.8132. Min Range: -7.8132

Max Act: 5.8466. Min Act: -0.0000

Data Index: 616350 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 7.8132. Min Range: -7.8132

Max Act: 6.2311. Min Act: -0.0000

Data Index: 380250 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 7.8132. Min Range: -7.8132

Max Act: 6.0421. Min Act: -0.0000

Data Index: 1312315 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 7.8132. Min Range: -7.8132

Max Act: 6.3269. Min Act: -0.0000

Data Index: 710725 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 7.8132. Min Range: -7.8132

Max Act: 6.2541. Min Act: -0.0000

Data Index: 552160 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 7.8132. Min Range: -7.8132

Max Act: 5.8659. Min Act: -0.0000

Data Index: 144796 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 7.8132. Min Range: -7.8132

Max Act: 5.8637. Min Act: -0.0000

Data Index: 794907 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 7.8132. Min Range: -7.8132

Max Act: 5.8750. Min Act: -0.0000

Data Index: 791639 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 7.8132. Min Range: -7.8132

Max Act: 6.0422. Min Act: -0.0000

Data Index: 72377 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 7.8132. Min Range: -7.8132

Max Act: 6.2105. Min Act: -0.0000

Data Index: 525579 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 7.8132. Min Range: -7.8132

Max Act: 5.7786. Min Act: -0.0000

Data Index: 698480 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 7.8132. Min Range: -7.8132

Max Act: 5.8887. Min Act: -0.0000

Data Index: 140022 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 7.8132. Min Range: -7.8132

Max Act: 5.7256. Min Act: -0.0000

Data Index: 1164897 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 7.8132. Min Range: -7.8132

Max Act: 5.8509. Min Act: -0.0000

Data Index: 956786 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 7.8132. Min Range: -7.8132

Max Act: 5.6610. Min Act: -0.0000

Data Index: 30165 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 7.8132. Min Range: -7.8132

Max Act: 6.0490. Min Act: -0.0000

Data Index: 660127 (C4 (Web Text))

Max Activating Token Index: 752