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

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

Neuron 3697 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.8459. Min Act: -0.0001

Data Index: 59196 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.8398. Min Act: -0.0001

Data Index: 697200 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.7022. Min Act: -0.0001

Data Index: 741373 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.7809. Min Act: -0.0001

Data Index: 35324 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.7933. Min Act: -0.0001

Data Index: 407592 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.5861. Min Act: -0.0001

Data Index: 537031 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.6908. Min Act: -0.0001

Data Index: 590719 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.6299. Min Act: -0.0001

Data Index: 337903 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.6991. Min Act: -0.0001

Data Index: 1162488 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.7393. Min Act: -0.0001

Data Index: 371799 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.6530. Min Act: -0.0001

Data Index: 530578 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.7026. Min Act: -0.0001

Data Index: 529939 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.6532. Min Act: -0.0001

Data Index: 225249 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.7048. Min Act: -0.0001

Data Index: 676263 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.6542. Min Act: -0.0001

Data Index: 106483 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.5468. Min Act: -0.0001

Data Index: 190615 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.6087. Min Act: -0.0001

Data Index: 922407 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.6336. Min Act: -0.0001

Data Index: 217648 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.5811. Min Act: -0.0001

Data Index: 288367 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.8459. Min Range: -0.8459

Max Act: 0.6514. Min Act: -0.0001

Data Index: 244919 (C4 (Web Text))

Max Activating Token Index: 956