Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 99 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.2689. Min Act: -0.0000

Data Index: 1022087 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1351200 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.1179. Min Act: -0.0000

Data Index: 646541 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.0012. Min Act: -0.0000

Data Index: 349885 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1214009 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.8965. Min Act: -0.0000

Data Index: 360549 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.9737. Min Act: -0.0000

Data Index: 278055 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.0658. Min Act: -0.0000

Data Index: 306517 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.8915. Min Act: -0.0000

Data Index: 830510 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.9346. Min Act: -0.0000

Data Index: 1400233 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.8828. Min Act: -0.0000

Data Index: 915332 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1007323 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1106300 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.8516. Min Act: -0.0000

Data Index: 2830 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1035478 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.7376. Min Act: -0.0000

Data Index: 457868 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.8344. Min Act: -0.0000

Data Index: 791289 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1018762 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.7893. Min Act: -0.0000

Data Index: 589168 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1224023 (C4 (Web Text))

Max Activating Token Index: 382