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

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

Neuron 1771 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.4348. Min Act: -0.0002

Data Index: 981921 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.3851. Min Act: -0.0003

Data Index: 144885 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.3588. Min Act: -0.0002

Data Index: 735489 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.3359. Min Act: -0.0002

Data Index: 223043 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2902. Min Act: -0.0002

Data Index: 101068 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2887. Min Act: -0.0002

Data Index: 1234625 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2667. Min Act: -0.0002

Data Index: 1171114 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2778. Min Act: -0.0003

Data Index: 148756 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2783. Min Act: -0.0002

Data Index: 916272 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2885. Min Act: -0.0002

Data Index: 420567 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2840. Min Act: -0.0002

Data Index: 1089029 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2544. Min Act: -0.0002

Data Index: 917466 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2491. Min Act: -0.0002

Data Index: 84408 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2594. Min Act: -0.0003

Data Index: 807397 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2480. Min Act: -0.0002

Data Index: 745765 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2396. Min Act: -0.0002

Data Index: 1339715 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2396. Min Act: -0.0002

Data Index: 593642 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2258. Min Act: -0.0002

Data Index: 164362 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2085. Min Act: -0.0003

Data Index: 730083 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2062. Min Act: -0.0002

Data Index: 1264791 (C4 (Web Text))

Max Activating Token Index: 519