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

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

Neuron 1119 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2569. Min Range: -3.2569

Max Act: 3.2569. Min Act: -0.0000

Data Index: 1243926 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.8887. Min Act: -0.0000

Data Index: 103153 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.1213. Min Act: -0.0000

Data Index: 476884 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.1566. Min Act: -0.0000

Data Index: 648781 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 3.2569. Min Range: -3.2569

Max Act: 1.9286. Min Act: -0.0000

Data Index: 939439 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 3.2569. Min Range: -3.2569

Max Act: 1.0885. Min Act: 0.0001

Data Index: 146321 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.7799. Min Act: 0.0001

Data Index: 29565 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.7334. Min Act: 0.0000

Data Index: 766471 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.7619. Min Act: 0.0001

Data Index: 869604 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.7153. Min Act: -0.0000

Data Index: 145575 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.7208. Min Act: 0.0001

Data Index: 510614 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.7112. Min Act: 0.0000

Data Index: 562546 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.6971. Min Act: 0.0000

Data Index: 1106505 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.6786. Min Act: 0.0000

Data Index: 918518 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.7024. Min Act: 0.0000

Data Index: 596192 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.7008. Min Act: 0.0000

Data Index: 615068 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.6906. Min Act: -0.0000

Data Index: 954198 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.6643. Min Act: 0.0000

Data Index: 534534 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.6724. Min Act: 0.0001

Data Index: 615098 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 3.2569. Min Range: -3.2569

Max Act: 0.6409. Min Act: 0.0000

Data Index: 328888 (C4 (Web Text))

Max Activating Token Index: 779