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

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

Neuron 6116 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: 0.1459. Min Range: -0.1459

Max Act: 0.1425. Min Act: -0.0000

Data Index: 850770 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1459. Min Act: -0.0000

Data Index: 56208 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1128. Min Act: -0.0000

Data Index: 355650 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1249. Min Act: -0.0000

Data Index: 431231 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1305. Min Act: -0.0000

Data Index: 78114 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1063. Min Act: -0.0000

Data Index: 795615 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1078638 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1422511 (Python Code)

Max Activating Token Index: 733

Text #8

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1112591 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1020. Min Act: -0.0000

Data Index: 929157 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1126885 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1006. Min Act: -0.0000

Data Index: 241586 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1114367 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.0995. Min Act: -0.0000

Data Index: 30168 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1201611 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1365318 (Python Code)

Max Activating Token Index: 400

Text #16

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1298562 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.0986. Min Act: -0.0000

Data Index: 221497 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.0923. Min Act: -0.0000

Data Index: 383668 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.0955. Min Act: -0.0000

Data Index: 93217 (C4 (Web Text))

Max Activating Token Index: 619