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

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

Neuron 3759 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.7597. Min Range: -8.7597

Max Act: 8.7597. Min Act: -0.0000

Data Index: 828658 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 8.7597. Min Range: -8.7597

Max Act: 8.7343. Min Act: -0.0000

Data Index: 752913 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 8.7597. Min Range: -8.7597

Max Act: 8.3721. Min Act: -0.0000

Data Index: 1242803 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 8.7597. Min Range: -8.7597

Max Act: 7.9465. Min Act: -0.0000

Data Index: 277363 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 8.7597. Min Range: -8.7597

Max Act: 8.5821. Min Act: -0.0000

Data Index: 847400 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 8.7597. Min Range: -8.7597

Max Act: 7.4941. Min Act: -0.0000

Data Index: 167818 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 8.7597. Min Range: -8.7597

Max Act: 7.2750. Min Act: -0.0000

Data Index: 352508 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 8.7597. Min Range: -8.7597

Max Act: 7.4482. Min Act: -0.0000

Data Index: 451441 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 8.7597. Min Range: -8.7597

Max Act: 7.3464. Min Act: -0.0000

Data Index: 510271 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 8.7597. Min Range: -8.7597

Max Act: 7.0271. Min Act: -0.0000

Data Index: 433501 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 8.7597. Min Range: -8.7597

Max Act: 7.2107. Min Act: -0.0000

Data Index: 1196960 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 8.7597. Min Range: -8.7597

Max Act: 6.9629. Min Act: -0.0000

Data Index: 501780 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 8.7597. Min Range: -8.7597

Max Act: 6.9555. Min Act: -0.0000

Data Index: 1283130 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 8.7597. Min Range: -8.7597

Max Act: 7.4769. Min Act: -0.0000

Data Index: 46011 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 8.7597. Min Range: -8.7597

Max Act: 6.8201. Min Act: -0.0000

Data Index: 530364 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 8.7597. Min Range: -8.7597

Max Act: 7.1748. Min Act: -0.0000

Data Index: 705405 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 8.7597. Min Range: -8.7597

Max Act: 6.5698. Min Act: -0.0000

Data Index: 1133983 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 8.7597. Min Range: -8.7597

Max Act: 6.8935. Min Act: -0.0000

Data Index: 1069391 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 8.7597. Min Range: -8.7597

Max Act: 6.8978. Min Act: -0.0000

Data Index: 893310 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 8.7597. Min Range: -8.7597

Max Act: 6.8734. Min Act: -0.0000

Data Index: 1105543 (C4 (Web Text))

Max Activating Token Index: 700