Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1991 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7986. Min Act: -0.0001

Data Index: 330485 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7161. Min Act: -0.0001

Data Index: 1346503 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7151. Min Act: -0.0001

Data Index: 1034324 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7362. Min Act: -0.0001

Data Index: 1048969 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6987. Min Act: -0.0001

Data Index: 585733 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6252. Min Act: -0.0001

Data Index: 1182328 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6362. Min Act: -0.0001

Data Index: 92503 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6657. Min Act: -0.0001

Data Index: 873810 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6423. Min Act: -0.0001

Data Index: 272774 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6377. Min Act: -0.0001

Data Index: 431058 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6484. Min Act: -0.0001

Data Index: 1196706 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6584. Min Act: -0.0001

Data Index: 180221 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6766. Min Act: -0.0001

Data Index: 1035703 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6287. Min Act: -0.0001

Data Index: 1110413 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6127. Min Act: -0.0001

Data Index: 853160 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6099. Min Act: -0.0001

Data Index: 1347107 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6292. Min Act: -0.0001

Data Index: 1002567 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6090. Min Act: -0.0001

Data Index: 1266853 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6034. Min Act: -0.0001

Data Index: 40791 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6079. Min Act: -0.0001

Data Index: 272762 (C4 (Web Text))

Max Activating Token Index: 225