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

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

Neuron 1415 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7912. Min Act: -0.0001

Data Index: 1015390 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7464. Min Act: -0.0001

Data Index: 1097133 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7738. Min Act: -0.0001

Data Index: 382976 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7434. Min Act: -0.0001

Data Index: 92610 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7184. Min Act: -0.0001

Data Index: 1003818 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7031. Min Act: -0.0001

Data Index: 1214705 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6231. Min Act: -0.0001

Data Index: 1070289 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6615. Min Act: -0.0001

Data Index: 371412 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6915. Min Act: -0.0001

Data Index: 604007 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6287. Min Act: -0.0001

Data Index: 900393 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6647. Min Act: -0.0001

Data Index: 119252 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6338. Min Act: -0.0001

Data Index: 725449 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.7154. Min Act: -0.0001

Data Index: 982335 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6285. Min Act: -0.0001

Data Index: 1258955 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6514. Min Act: -0.0001

Data Index: 1139439 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6696. Min Act: -0.0001

Data Index: 197278 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.5310. Min Act: -0.0001

Data Index: 451424 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.5813. Min Act: -0.0001

Data Index: 554624 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.6582. Min Act: -0.0001

Data Index: 735889 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.7912. Min Range: -0.7912

Max Act: 0.5351. Min Act: -0.0001

Data Index: 227735 (C4 (Web Text))

Max Activating Token Index: 428