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

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

Neuron 511 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: 1.1123. Min Range: -1.1123

Max Act: 1.1123. Min Act: -0.0003

Data Index: 42115 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.1123. Min Range: -1.1123

Max Act: 1.0684. Min Act: -0.0002

Data Index: 562147 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 1.1123. Min Range: -1.1123

Max Act: 1.0513. Min Act: -0.0002

Data Index: 295541 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 1.1123. Min Range: -1.1123

Max Act: 1.0023. Min Act: -0.0002

Data Index: 663128 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 1.1123. Min Range: -1.1123

Max Act: 1.0015. Min Act: -0.0002

Data Index: 594459 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 1.1123. Min Range: -1.1123

Max Act: 1.0226. Min Act: -0.0002

Data Index: 735767 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 1.1123. Min Range: -1.1123

Max Act: 1.0020. Min Act: -0.0002

Data Index: 893631 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9704. Min Act: -0.0002

Data Index: 566526 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9916. Min Act: -0.0002

Data Index: 263608 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9738. Min Act: -0.0002

Data Index: 41189 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9692. Min Act: -0.0002

Data Index: 840554 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9725. Min Act: -0.0002

Data Index: 1256454 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9633. Min Act: -0.0003

Data Index: 1141340 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9565. Min Act: -0.0002

Data Index: 1067688 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9568. Min Act: -0.0003

Data Index: 322173 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9409. Min Act: -0.0002

Data Index: 816053 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9503. Min Act: -0.0002

Data Index: 1277843 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9315. Min Act: -0.0003

Data Index: 643026 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9447. Min Act: -0.0002

Data Index: 172016 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 1.1123. Min Range: -1.1123

Max Act: 0.9284. Min Act: -0.0002

Data Index: 795277 (C4 (Web Text))

Max Activating Token Index: 980