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

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

Neuron 2676 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4478. Min Act: -0.0001

Data Index: 1355969 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4468. Min Act: -0.0001

Data Index: 411913 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4411. Min Act: -0.0001

Data Index: 1098600 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3749. Min Act: -0.0001

Data Index: 737452 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3879. Min Act: -0.0001

Data Index: 744787 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3752. Min Act: -0.0001

Data Index: 176995 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3888. Min Act: -0.0001

Data Index: 1331734 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3902. Min Act: -0.0001

Data Index: 72991 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3727. Min Act: -0.0001

Data Index: 9034 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3528. Min Act: -0.0001

Data Index: 596128 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3449. Min Act: -0.0001

Data Index: 890911 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3408. Min Act: -0.0001

Data Index: 115269 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3381. Min Act: -0.0001

Data Index: 333736 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3309. Min Act: -0.0001

Data Index: 176473 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3035. Min Act: -0.0001

Data Index: 962789 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3227. Min Act: -0.0001

Data Index: 1136824 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3339. Min Act: -0.0001

Data Index: 68342 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3407. Min Act: -0.0001

Data Index: 46761 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3274. Min Act: -0.0001

Data Index: 785345 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3287. Min Act: -0.0001

Data Index: 323818 (C4 (Web Text))

Max Activating Token Index: 79