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

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

Neuron 3304 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: 4.7696. Min Range: -4.7696

Max Act: 4.7696. Min Act: -0.0000

Data Index: 1135280 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.0256. Min Act: -0.0000

Data Index: 512723 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.9464. Min Act: -0.0000

Data Index: 1206562 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.7252. Min Act: -0.0000

Data Index: 926869 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.7387. Min Act: -0.0000

Data Index: 42723 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.8573. Min Act: -0.0000

Data Index: 506853 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.5776. Min Act: -0.0000

Data Index: 395508 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.3934. Min Act: -0.0000

Data Index: 795836 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.6579. Min Act: -0.0000

Data Index: 239608 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.4567. Min Act: -0.0000

Data Index: 237680 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.3314. Min Act: -0.0000

Data Index: 450191 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.4158. Min Act: -0.0000

Data Index: 873857 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.4001. Min Act: -0.0000

Data Index: 31608 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.3933. Min Act: -0.0000

Data Index: 1035170 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.4881. Min Act: -0.0000

Data Index: 83921 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.1901. Min Act: -0.0000

Data Index: 1078202 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.1493. Min Act: -0.0000

Data Index: 1198959 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.1522. Min Act: -0.0000

Data Index: 1121691 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.1364. Min Act: -0.0000

Data Index: 1165445 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 4.7696. Min Range: -4.7696

Max Act: 2.1437. Min Act: -0.0000

Data Index: 34238 (C4 (Web Text))

Max Activating Token Index: 459