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

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

Neuron 675 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: 2.8490. Min Range: -2.8490

Max Act: 2.6250. Min Act: -0.0000

Data Index: 113653 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.5906. Min Act: -0.0000

Data Index: 813541 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.8490. Min Act: -0.0000

Data Index: 453731 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.3203. Min Act: -0.0000

Data Index: 947241 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.3855. Min Act: -0.0000

Data Index: 221614 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.1872. Min Act: -0.0000

Data Index: 1289612 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.2815. Min Act: -0.0000

Data Index: 953170 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.2390. Min Act: -0.0000

Data Index: 743046 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.0705. Min Act: -0.0000

Data Index: 772782 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.0546. Min Act: -0.0000

Data Index: 735920 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.0454. Min Act: -0.0000

Data Index: 1350654 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.0362. Min Act: -0.0000

Data Index: 1024472 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.1538. Min Act: -0.0000

Data Index: 330743 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.2268. Min Act: -0.0000

Data Index: 1283676 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.0996. Min Act: -0.0000

Data Index: 136003 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.0206. Min Act: -0.0000

Data Index: 757036 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.1921. Min Act: -0.0000

Data Index: 266133 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.2061. Min Act: -0.0000

Data Index: 759453 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 2.8490. Min Range: -2.8490

Max Act: 2.0483. Min Act: -0.0000

Data Index: 1232518 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 2.8490. Min Range: -2.8490

Max Act: 1.9027. Min Act: -0.0000

Data Index: 897703 (C4 (Web Text))

Max Activating Token Index: 498