Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1962 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.6206. Min Act: -0.0001

Data Index: 465646 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5814. Min Act: -0.0001

Data Index: 721621 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.6183. Min Act: -0.0001

Data Index: 1016483 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5996. Min Act: -0.0001

Data Index: 175364 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.6290. Min Act: -0.0001

Data Index: 401042 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5844. Min Act: -0.0001

Data Index: 971360 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5826. Min Act: -0.0001

Data Index: 684976 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5950. Min Act: -0.0001

Data Index: 891512 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5576. Min Act: -0.0001

Data Index: 744306 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5737. Min Act: -0.0001

Data Index: 558669 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5499. Min Act: -0.0001

Data Index: 587009 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5459. Min Act: -0.0001

Data Index: 402600 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5601. Min Act: -0.0001

Data Index: 111651 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5562. Min Act: -0.0001

Data Index: 772486 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5061. Min Act: -0.0001

Data Index: 1308562 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5419. Min Act: -0.0001

Data Index: 596798 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5322. Min Act: -0.0001

Data Index: 125964 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5291. Min Act: -0.0000

Data Index: 489860 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5469. Min Act: -0.0001

Data Index: 232574 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5278. Min Act: -0.0001

Data Index: 477211 (C4 (Web Text))

Max Activating Token Index: 841