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

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

Neuron 2992 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3735. Min Range: -6.3735

Max Act: 6.3735. Min Act: -0.0000

Data Index: 613692 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 6.3735. Min Range: -6.3735

Max Act: 6.2956. Min Act: -0.0000

Data Index: 1047793 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 6.3735. Min Range: -6.3735

Max Act: 5.9653. Min Act: -0.0000

Data Index: 293546 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 6.3735. Min Range: -6.3735

Max Act: 6.1865. Min Act: -0.0000

Data Index: 1207808 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 6.3735. Min Range: -6.3735

Max Act: 5.7417. Min Act: -0.0000

Data Index: 194911 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 6.3735. Min Range: -6.3735

Max Act: 5.8986. Min Act: -0.0000

Data Index: 1267492 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 6.3735. Min Range: -6.3735

Max Act: 5.4604. Min Act: -0.0000

Data Index: 1022872 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.8997. Min Act: -0.0000

Data Index: 411933 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.8862. Min Act: -0.0000

Data Index: 812678 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.9763. Min Act: -0.0000

Data Index: 373582 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.5258. Min Act: -0.0000

Data Index: 1346288 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.6893. Min Act: -0.0000

Data Index: 106669 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.6700. Min Act: -0.0000

Data Index: 387910 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.4966. Min Act: -0.0000

Data Index: 655139 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.6819. Min Act: -0.0000

Data Index: 601260 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.3426. Min Act: -0.0000

Data Index: 405971 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.3993. Min Act: -0.0000

Data Index: 219797 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.6184. Min Act: -0.0000

Data Index: 156215 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.1952. Min Act: -0.0000

Data Index: 129962 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 6.3735. Min Range: -6.3735

Max Act: 4.2823. Min Act: -0.0000

Data Index: 825498 (C4 (Web Text))

Max Activating Token Index: 66