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

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

Neuron 3036 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.2286. Min Act: -0.0001

Data Index: 1382206 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.2015. Min Act: -0.0001

Data Index: 1441119 (Python Code)

Max Activating Token Index: 797

Text #2

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.0153. Min Act: -0.0001

Data Index: 1178683 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9292. Min Act: -0.0001

Data Index: 728021 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9496. Min Act: -0.0001

Data Index: 36537 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9411. Min Act: -0.0001

Data Index: 1233673 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9049. Min Act: -0.0001

Data Index: 1453923 (Python Code)

Max Activating Token Index: 248

Text #7

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8758. Min Act: -0.0001

Data Index: 942898 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9319. Min Act: -0.0001

Data Index: 987441 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9197. Min Act: -0.0001

Data Index: 1267659 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8728. Min Act: -0.0001

Data Index: 234937 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9035. Min Act: -0.0001

Data Index: 248152 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8942. Min Act: -0.0001

Data Index: 850454 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8901. Min Act: -0.0001

Data Index: 1536606 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8316. Min Act: -0.0001

Data Index: 260276 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8874. Min Act: -0.0001

Data Index: 80387 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8262. Min Act: -0.0001

Data Index: 260687 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7968. Min Act: -0.0001

Data Index: 868126 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8664. Min Act: -0.0001

Data Index: 676797 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8451. Min Act: -0.0001

Data Index: 356661 (C4 (Web Text))

Max Activating Token Index: 944