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

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

Neuron 3044 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5273. Min Range: -2.5273

Max Act: 2.5273. Min Act: 0.0000

Data Index: 315957 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 2.5273. Min Range: -2.5273

Max Act: 2.4429. Min Act: -0.0000

Data Index: 981919 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 2.5273. Min Range: -2.5273

Max Act: 1.9247. Min Act: -0.0000

Data Index: 1040731 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 2.5273. Min Range: -2.5273

Max Act: 1.4576. Min Act: -0.0000

Data Index: 598304 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 2.5273. Min Range: -2.5273

Max Act: 1.3619. Min Act: -0.0000

Data Index: 1065151 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 2.5273. Min Range: -2.5273

Max Act: 1.2492. Min Act: -0.0000

Data Index: 221395 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 2.5273. Min Range: -2.5273

Max Act: 1.1182. Min Act: -0.0000

Data Index: 1293118 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 2.5273. Min Range: -2.5273

Max Act: 1.0040. Min Act: -0.0000

Data Index: 54354 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.8310. Min Act: -0.0000

Data Index: 757605 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.8311. Min Act: -0.0000

Data Index: 360902 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1200911 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1281362 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.7210. Min Act: -0.0000

Data Index: 150717 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.7277. Min Act: -0.0000

Data Index: 83614 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1004707 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.7233. Min Act: -0.0000

Data Index: 777270 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.6746. Min Act: -0.0000

Data Index: 616803 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.6272. Min Act: -0.0000

Data Index: 962665 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1118032 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 2.5273. Min Range: -2.5273

Max Act: 0.6801. Min Act: -0.0000

Data Index: 413248 (C4 (Web Text))

Max Activating Token Index: 450