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

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

Neuron 3718 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0768. Min Act: -0.0000

Data Index: 485912 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1098165 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8789. Min Act: -0.0000

Data Index: 262634 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8823. Min Act: -0.0000

Data Index: 466730 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8611. Min Act: -0.0000

Data Index: 582905 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1072615 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8820. Min Act: -0.0000

Data Index: 917538 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8277. Min Act: -0.0000

Data Index: 945593 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1131622 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8121. Min Act: -0.0000

Data Index: 990681 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8136. Min Act: -0.0000

Data Index: 680371 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8114. Min Act: -0.0000

Data Index: 99922 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7402. Min Act: -0.0000

Data Index: 791589 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7958. Min Act: -0.0000

Data Index: 725183 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7969. Min Act: -0.0000

Data Index: 290564 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8488. Min Act: -0.0000

Data Index: 954485 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7880. Min Act: -0.0000

Data Index: 783537 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7373. Min Act: -0.0000

Data Index: 350689 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1133666 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7488. Min Act: -0.0000

Data Index: 930806 (C4 (Web Text))

Max Activating Token Index: 997