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

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

Neuron 2270 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7077. Min Range: -2.7077

Max Act: 2.7077. Min Act: -0.0000

Data Index: 91686 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 2.7077. Min Range: -2.7077

Max Act: 2.6920. Min Act: -0.0000

Data Index: 919748 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.9738. Min Act: -0.0000

Data Index: 263026 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.6211. Min Act: -0.0000

Data Index: 572926 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.6244. Min Act: -0.0000

Data Index: 639667 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1092173 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.3399. Min Act: -0.0000

Data Index: 63864 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.3163. Min Act: -0.0000

Data Index: 511574 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.3085. Min Act: -0.0000

Data Index: 393343 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.2500. Min Act: -0.0000

Data Index: 710309 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.2517. Min Act: -0.0000

Data Index: 1163696 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.2506. Min Act: -0.0000

Data Index: 903442 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.2963. Min Act: -0.0000

Data Index: 548508 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.1519. Min Act: 0.0000

Data Index: 529266 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.2172. Min Act: -0.0000

Data Index: 400598 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.1452. Min Act: -0.0000

Data Index: 662643 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.1894. Min Act: -0.0000

Data Index: 645927 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.1285. Min Act: -0.0000

Data Index: 770544 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.1557. Min Act: -0.0000

Data Index: 572206 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 2.7077. Min Range: -2.7077

Max Act: 1.1408. Min Act: -0.0000

Data Index: 979300 (C4 (Web Text))

Max Activating Token Index: 748