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

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

Neuron 2457 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: 0.9705. Min Range: -0.9705

Max Act: 0.9535. Min Act: -0.0002

Data Index: 1170524 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.9705. Min Act: -0.0002

Data Index: 788013 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.9492. Min Act: -0.0002

Data Index: 1038781 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.9184. Min Act: -0.0003

Data Index: 252000 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.9256. Min Act: -0.0002

Data Index: 8649 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8953. Min Act: -0.0002

Data Index: 883076 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8934. Min Act: -0.0002

Data Index: 513997 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8730. Min Act: -0.0002

Data Index: 901572 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8547. Min Act: -0.0002

Data Index: 937324 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8545. Min Act: -0.0003

Data Index: 733654 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8531. Min Act: -0.0002

Data Index: 590914 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8695. Min Act: -0.0002

Data Index: 551741 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8590. Min Act: -0.0002

Data Index: 271073 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8343. Min Act: -0.0002

Data Index: 797782 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8499. Min Act: -0.0002

Data Index: 50280 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8398. Min Act: -0.0002

Data Index: 1308331 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8287. Min Act: -0.0002

Data Index: 1224590 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8193. Min Act: -0.0002

Data Index: 454476 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8250. Min Act: -0.0002

Data Index: 429458 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8103. Min Act: -0.0002

Data Index: 663911 (C4 (Web Text))

Max Activating Token Index: 585