Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2755 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.6044. Min Act: -0.0001

Data Index: 1105801 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.3198. Min Act: -0.0001

Data Index: 1127991 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 5.6044. Min Range: -5.6044

Max Act: 4.5249. Min Act: -0.0001

Data Index: 1351397 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 5.6044. Min Range: -5.6044

Max Act: 4.6414. Min Act: -0.0001

Data Index: 969776 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 5.6044. Min Range: -5.6044

Max Act: 4.3436. Min Act: -0.0001

Data Index: 1355398 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 5.6044. Min Range: -5.6044

Max Act: 4.1548. Min Act: -0.0001

Data Index: 990411 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.4861. Min Act: -0.0001

Data Index: 1002300 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.7111. Min Act: -0.0001

Data Index: 937162 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.8176. Min Act: -0.0001

Data Index: 103162 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.7437. Min Act: -0.0001

Data Index: 1190482 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.7468. Min Act: -0.0001

Data Index: 56685 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.5348. Min Act: -0.0001

Data Index: 628950 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.4061. Min Act: -0.0001

Data Index: 1351960 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.5998. Min Act: -0.0001

Data Index: 1356893 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.7582. Min Act: -0.0001

Data Index: 884078 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.8326. Min Act: -0.0001

Data Index: 224700 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.8238. Min Act: -0.0001

Data Index: 408304 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.5317. Min Act: -0.0001

Data Index: 336437 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.3513. Min Act: -0.0001

Data Index: 408071 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 5.6044. Min Range: -5.6044

Max Act: 3.6434. Min Act: -0.0001

Data Index: 1226836 (C4 (Web Text))

Max Activating Token Index: 734