Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5253 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3325. Min Range: -3.3325

Max Act: 3.3325. Min Act: -0.0000

Data Index: 314943 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.8088. Min Act: -0.0000

Data Index: 1171701 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.7791. Min Act: -0.0000

Data Index: 1371513 (Python Code)

Max Activating Token Index: 969

Text #3

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.5799. Min Act: -0.0000

Data Index: 158656 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.5650. Min Act: -0.0000

Data Index: 1563693 (Python Code)

Max Activating Token Index: 824

Text #5

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.1214. Min Act: -0.0000

Data Index: 490095 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.3612. Min Act: -0.0000

Data Index: 1157781 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.5569. Min Act: -0.0000

Data Index: 1227397 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.4360. Min Act: -0.0000

Data Index: 1584930 (Python Code)

Max Activating Token Index: 230

Text #9

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.3118. Min Act: -0.0000

Data Index: 784307 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.2795. Min Act: -0.0000

Data Index: 1361619 (Python Code)

Max Activating Token Index: 890

Text #11

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.4283. Min Act: -0.0000

Data Index: 337559 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.4025. Min Act: -0.0000

Data Index: 135391 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.2399. Min Act: -0.0000

Data Index: 48451 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.3550. Min Act: -0.0000

Data Index: 440781 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.2404. Min Act: -0.0000

Data Index: 257949 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.0912. Min Act: -0.0000

Data Index: 1092013 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.0919. Min Act: -0.0000

Data Index: 469519 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.4286. Min Act: -0.0000

Data Index: 1063194 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 3.3325. Min Range: -3.3325

Max Act: 2.3074. Min Act: -0.0000

Data Index: 865242 (C4 (Web Text))

Max Activating Token Index: 679