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

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

Neuron 5182 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2756. Min Range: -1.2756

Max Act: 1.2756. Min Act: -0.0000

Data Index: 532711 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 1.2756. Min Range: -1.2756

Max Act: 1.0835. Min Act: -0.0000

Data Index: 784927 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 1.2756. Min Range: -1.2756

Max Act: 1.1797. Min Act: -0.0000

Data Index: 745290 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.2756. Min Range: -1.2756

Max Act: 1.0273. Min Act: -0.0000

Data Index: 1048147 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.9529. Min Act: -0.0000

Data Index: 897553 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8657. Min Act: -0.0000

Data Index: 69947 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1221796 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1106969 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8787. Min Act: -0.0000

Data Index: 868324 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8068. Min Act: -0.0000

Data Index: 664670 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7803. Min Act: 0.0000

Data Index: 286665 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.6951. Min Act: 0.0000

Data Index: 1341809 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1166517 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.6732. Min Act: -0.0000

Data Index: 18876 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1306464 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1157233 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7188. Min Act: -0.0000

Data Index: 539262 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.6892. Min Act: 0.0000

Data Index: 374562 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1315992 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.6739. Min Act: -0.0000

Data Index: 306739 (C4 (Web Text))

Max Activating Token Index: 335