Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2847 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.6835. Min Act: -0.0000

Data Index: 514345 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.6517. Min Act: -0.0000

Data Index: 836012 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1299378 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4641. Min Act: -0.0000

Data Index: 390498 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4758. Min Act: -0.0000

Data Index: 702079 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4493. Min Act: -0.0000

Data Index: 811154 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4439. Min Act: -0.0000

Data Index: 571353 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4198. Min Act: -0.0000

Data Index: 538864 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.3965. Min Act: -0.0000

Data Index: 165770 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4041. Min Act: -0.0000

Data Index: 394475 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1078176 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4325. Min Act: -0.0000

Data Index: 12858 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1295977 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1288806 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.3914. Min Act: -0.0000

Data Index: 262246 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.3700. Min Act: -0.0000

Data Index: 565365 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.3687. Min Act: -0.0000

Data Index: 635050 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1355124 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1196473 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.3816. Min Act: -0.0000

Data Index: 367744 (C4 (Web Text))

Max Activating Token Index: 174