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

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

Neuron 5318 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.7660. Min Act: -0.0000

Data Index: 803710 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.9396. Min Act: -0.0000

Data Index: 70247 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.9314. Min Act: -0.0000

Data Index: 1098997 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.8970. Min Act: -0.0000

Data Index: 1230213 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.8857. Min Act: -0.0000

Data Index: 172242 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.9665. Min Act: -0.0000

Data Index: 311255 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.7108. Min Act: -0.0000

Data Index: 543678 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.7513. Min Act: -0.0000

Data Index: 27053 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.7165. Min Act: -0.0000

Data Index: 598559 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.7817. Min Act: -0.0000

Data Index: 908832 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.7566. Min Act: -0.0000

Data Index: 931984 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.5532. Min Act: -0.0000

Data Index: 1249709 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.5520. Min Act: -0.0000

Data Index: 540793 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.5222. Min Act: -0.0000

Data Index: 407150 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.4776. Min Act: -0.0000

Data Index: 1191589 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.2595. Min Act: -0.0000

Data Index: 626005 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.9665. Min Range: -1.9665

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1204207 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 1.9665. Min Range: -1.9665

Max Act: 0.9410. Min Act: -0.0000

Data Index: 865751 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 1.9665. Min Range: -1.9665

Max Act: 0.9817. Min Act: -0.0000

Data Index: 573303 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.9665. Min Range: -1.9665

Max Act: 0.9703. Min Act: -0.0000

Data Index: 46989 (C4 (Web Text))

Max Activating Token Index: 392