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

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

Neuron 5964 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 12.8838. Min Range: -12.8838

Max Act: 12.8838. Min Act: -0.0000

Data Index: 756112 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 12.8838. Min Range: -12.8838

Max Act: 12.8369. Min Act: -0.0000

Data Index: 344593 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 12.8838. Min Range: -12.8838

Max Act: 12.3273. Min Act: -0.0000

Data Index: 1056919 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 12.8838. Min Range: -12.8838

Max Act: 12.5866. Min Act: -0.0000

Data Index: 409536 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 12.8838. Min Range: -12.8838

Max Act: 12.1777. Min Act: -0.0000

Data Index: 999512 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 12.8838. Min Range: -12.8838

Max Act: 12.0674. Min Act: -0.0000

Data Index: 735965 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 12.8838. Min Range: -12.8838

Max Act: 12.0192. Min Act: -0.0000

Data Index: 968847 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 12.8838. Min Range: -12.8838

Max Act: 11.7736. Min Act: -0.0000

Data Index: 173539 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 12.8838. Min Range: -12.8838

Max Act: 11.8540. Min Act: -0.0000

Data Index: 1336797 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 12.8838. Min Range: -12.8838

Max Act: 9.5675. Min Act: -0.0000

Data Index: 924860 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 12.8838. Min Range: -12.8838

Max Act: 6.2436. Min Act: -0.0000

Data Index: 116819 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 12.8838. Min Range: -12.8838

Max Act: 4.8377. Min Act: -0.0000

Data Index: 909646 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 12.8838. Min Range: -12.8838

Max Act: 4.5117. Min Act: -0.0000

Data Index: 142603 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 12.8838. Min Range: -12.8838

Max Act: 4.3969. Min Act: -0.0000

Data Index: 555866 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 12.8838. Min Range: -12.8838

Max Act: 4.1187. Min Act: 0.0000

Data Index: 292136 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 12.8838. Min Range: -12.8838

Max Act: 3.9758. Min Act: 0.0000

Data Index: 867601 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 12.8838. Min Range: -12.8838

Max Act: 3.4510. Min Act: -0.0000

Data Index: 549478 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 12.8838. Min Range: -12.8838

Max Act: 3.9193. Min Act: 0.0000

Data Index: 911853 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 12.8838. Min Range: -12.8838

Max Act: 3.5832. Min Act: 0.0000

Data Index: 52311 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 12.8838. Min Range: -12.8838

Max Act: 3.5976. Min Act: 0.0000

Data Index: 558630 (C4 (Web Text))

Max Activating Token Index: 713