Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2922 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.7011. Min Act: -0.0000

Data Index: 936405 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1336703 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.6546. Min Act: -0.0000

Data Index: 473474 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.6202. Min Act: -0.0001

Data Index: 1195258 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5774. Min Act: -0.0000

Data Index: 460364 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.6286. Min Act: -0.0001

Data Index: 637571 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5965. Min Act: -0.0001

Data Index: 759842 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5899. Min Act: -0.0000

Data Index: 657913 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5903. Min Act: -0.0000

Data Index: 240186 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5848. Min Act: -0.0000

Data Index: 451014 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5044. Min Act: -0.0000

Data Index: 69034 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5429. Min Act: -0.0001

Data Index: 365667 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5359. Min Act: -0.0001

Data Index: 1303115 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5342. Min Act: -0.0000

Data Index: 399349 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5567. Min Act: -0.0001

Data Index: 578914 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5512. Min Act: -0.0000

Data Index: 996752 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5509. Min Act: -0.0001

Data Index: 875538 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5678. Min Act: -0.0001

Data Index: 52325 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1314436 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.7019. Min Range: -0.7019

Max Act: 0.5199. Min Act: -0.0000

Data Index: 221933 (C4 (Web Text))

Max Activating Token Index: 223