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

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

Neuron 1996 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.8974. Min Act: -0.0002

Data Index: 1338384 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.7608. Min Act: -0.0002

Data Index: 646190 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5615. Min Act: -0.0002

Data Index: 675109 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5945. Min Act: -0.0002

Data Index: 374598 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.6195. Min Act: -0.0002

Data Index: 799343 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5382. Min Act: -0.0002

Data Index: 1344356 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.6074. Min Act: -0.0002

Data Index: 167710 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.7187. Min Act: -0.0001

Data Index: 1197520 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.7014. Min Act: -0.0002

Data Index: 727285 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5591. Min Act: -0.0002

Data Index: 511934 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.7051. Min Act: -0.0002

Data Index: 1190595 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5137. Min Act: -0.0002

Data Index: 800023 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.6400. Min Act: -0.0001

Data Index: 281556 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5663. Min Act: -0.0002

Data Index: 934392 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5390. Min Act: -0.0001

Data Index: 701887 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5862. Min Act: -0.0002

Data Index: 573901 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5699. Min Act: -0.0002

Data Index: 1305900 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5835. Min Act: -0.0002

Data Index: 204827 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.6953. Min Act: -0.0002

Data Index: 567585 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.6737. Min Act: -0.0002

Data Index: 884000 (C4 (Web Text))

Max Activating Token Index: 133