Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3566 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.8068. Min Act: -0.0001

Data Index: 1079408 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.7556. Min Act: -0.0001

Data Index: 458581 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.7961. Min Act: -0.0001

Data Index: 44475 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.7750. Min Act: -0.0001

Data Index: 809528 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.7206. Min Act: -0.0000

Data Index: 669353 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.7192. Min Act: -0.0001

Data Index: 180016 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.7379. Min Act: -0.0001

Data Index: 752350 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6812. Min Act: -0.0000

Data Index: 970925 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6957. Min Act: -0.0001

Data Index: 614736 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6811. Min Act: -0.0000

Data Index: 307147 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1260561 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6421. Min Act: -0.0001

Data Index: 604218 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1300635 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6593. Min Act: -0.0000

Data Index: 314644 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6767. Min Act: -0.0000

Data Index: 100722 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6743. Min Act: -0.0001

Data Index: 506019 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6520. Min Act: -0.0000

Data Index: 75762 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6050. Min Act: -0.0001

Data Index: 318961 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6632. Min Act: -0.0001

Data Index: 533508 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6295. Min Act: -0.0000

Data Index: 998475 (C4 (Web Text))

Max Activating Token Index: 455