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

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

Neuron 2560 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0450. Min Act: -0.0003

Data Index: 398022 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0465. Min Act: -0.0003

Data Index: 440832 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0451. Min Act: -0.0003

Data Index: 314944 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0436. Min Act: -0.0003

Data Index: 493138 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1186719 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0398. Min Act: -0.0003

Data Index: 137931 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0413. Min Act: -0.0003

Data Index: 215382 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0392. Min Act: -0.0003

Data Index: 492088 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0419. Min Act: -0.0003

Data Index: 376531 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0399. Min Act: -0.0003

Data Index: 284703 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1138162 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1022438 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1196333 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0403. Min Act: -0.0003

Data Index: 156064 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0396. Min Act: -0.0003

Data Index: 923873 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0373. Min Act: -0.0003

Data Index: 498178 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0395. Min Act: -0.0003

Data Index: 188898 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0397. Min Act: -0.0003

Data Index: 380590 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0432. Min Act: -0.0003

Data Index: 384975 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0390. Min Act: -0.0003

Data Index: 265336 (C4 (Web Text))

Max Activating Token Index: 261