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

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

Neuron 3612 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: 1.3196. Min Range: -1.3196

Max Act: 1.2565. Min Act: -0.0000

Data Index: 356330 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 1.3196. Min Range: -1.3196

Max Act: 1.3196. Min Act: -0.0000

Data Index: 678595 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 1.3196. Min Range: -1.3196

Max Act: 1.2296. Min Act: -0.0001

Data Index: 564466 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.3196. Min Range: -1.3196

Max Act: 1.1468. Min Act: -0.0001

Data Index: 778621 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 1.3196. Min Range: -1.3196

Max Act: 1.1656. Min Act: -0.0000

Data Index: 672129 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1132805 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9994. Min Act: -0.0000

Data Index: 1121763 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9578. Min Act: -0.0000

Data Index: 1190097 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9915. Min Act: -0.0000

Data Index: 346977 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1094900 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9614. Min Act: -0.0000

Data Index: 594640 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.8994. Min Act: -0.0001

Data Index: 549761 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.8696. Min Act: -0.0000

Data Index: 560458 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1144869 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.8449. Min Act: -0.0000

Data Index: 284694 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.8692. Min Act: -0.0000

Data Index: 285991 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.8150. Min Act: -0.0000

Data Index: 104675 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.7606. Min Act: -0.0000

Data Index: 26250 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1082611 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.8153. Min Act: -0.0000

Data Index: 82820 (C4 (Web Text))

Max Activating Token Index: 23