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

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

Neuron 387 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: 0.7335. Min Range: -0.7335

Max Act: 0.6475. Min Act: -0.0000

Data Index: 450664 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.7335. Min Act: -0.0000

Data Index: 626647 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6680. Min Act: -0.0000

Data Index: 480469 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1172152 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6453. Min Act: -0.0000

Data Index: 917369 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6471. Min Act: -0.0000

Data Index: 754722 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6035. Min Act: -0.0000

Data Index: 27534 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5935. Min Act: -0.0000

Data Index: 688954 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6311. Min Act: -0.0000

Data Index: 438331 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1266826 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1215603 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5750. Min Act: -0.0000

Data Index: 240036 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6098. Min Act: 0.0000

Data Index: 938303 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1248864 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5571. Min Act: -0.0000

Data Index: 353667 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5275. Min Act: -0.0000

Data Index: 747423 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5543. Min Act: 0.0000

Data Index: 1324596 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1287031 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1254055 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5315. Min Act: -0.0000

Data Index: 670999 (C4 (Web Text))

Max Activating Token Index: 413