Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 48 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.7553. Min Act: -0.0001

Data Index: 726740 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.5907. Min Act: -0.0001

Data Index: 1301630 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.5029. Min Act: -0.0001

Data Index: 619930 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.4724. Min Act: -0.0001

Data Index: 1142360 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.4391. Min Act: -0.0001

Data Index: 683995 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.4234. Min Act: -0.0001

Data Index: 1001750 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.4059. Min Act: -0.0001

Data Index: 838329 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.4217. Min Act: -0.0001

Data Index: 605297 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.3083. Min Act: -0.0001

Data Index: 999932 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.3779. Min Act: -0.0001

Data Index: 294689 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.3348. Min Act: -0.0001

Data Index: 1266090 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.2720. Min Act: -0.0001

Data Index: 165002 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.3071. Min Act: -0.0001

Data Index: 1127214 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.2723. Min Act: -0.0001

Data Index: 296819 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.3016. Min Act: -0.0001

Data Index: 1291176 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.2923. Min Act: -0.0001

Data Index: 163692 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.2892. Min Act: -0.0001

Data Index: 801298 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.2852. Min Act: -0.0001

Data Index: 986564 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.2157. Min Act: -0.0001

Data Index: 135532 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 1.7553. Min Range: -1.7553

Max Act: 1.2328. Min Act: -0.0001

Data Index: 703661 (C4 (Web Text))

Max Activating Token Index: 736