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

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

Neuron 303 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1240431 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1398965 (Python Code)

Max Activating Token Index: 182

Text #2

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1636588 (Python Code)

Max Activating Token Index: 557

Text #3

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1577905 (Python Code)

Max Activating Token Index: 506

Text #4

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3097. Min Act: -0.0000

Data Index: 656141 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1547330 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2955. Min Act: -0.0000

Data Index: 756450 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2655. Min Act: -0.0000

Data Index: 407325 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2714. Min Act: -0.0000

Data Index: 491258 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2564. Min Act: -0.0000

Data Index: 129636 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2515. Min Act: -0.0000

Data Index: 436277 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2512. Min Act: -0.0000

Data Index: 966867 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1601610 (Python Code)

Max Activating Token Index: 608

Text #13

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1105799 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2485. Min Act: -0.0000

Data Index: 712323 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2422. Min Act: -0.0000

Data Index: 287169 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2505. Min Act: 0.0000

Data Index: 178910 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1026888 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2398. Min Act: -0.0000

Data Index: 458997 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2434. Min Act: -0.0000

Data Index: 90041 (C4 (Web Text))

Max Activating Token Index: 398