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

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

Neuron 4913 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.4449. Min Act: -0.0000

Data Index: 801929 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.1891. Min Act: -0.0000

Data Index: 298042 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.1634. Min Act: -0.0000

Data Index: 3712 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.1266. Min Act: -0.0000

Data Index: 93352 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.0474. Min Act: -0.0000

Data Index: 281502 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.1139. Min Act: -0.0000

Data Index: 895002 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.0949. Min Act: -0.0000

Data Index: 49938 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1309157 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.0672. Min Act: -0.0000

Data Index: 306517 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.0601. Min Act: -0.0000

Data Index: 863029 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1013749 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 1.4449. Min Range: -1.4449

Max Act: 0.9949. Min Act: -0.0000

Data Index: 541578 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.0306. Min Act: -0.0000

Data Index: 61797 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.1050. Min Act: -0.0000

Data Index: 1293570 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.0169. Min Act: -0.0000

Data Index: 483815 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.4449. Min Range: -1.4449

Max Act: 1.0004. Min Act: -0.0000

Data Index: 619548 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 1.4449. Min Range: -1.4449

Max Act: 0.9980. Min Act: -0.0000

Data Index: 234013 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 1.4449. Min Range: -1.4449

Max Act: 0.9838. Min Act: -0.0000

Data Index: 221247 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.4449. Min Range: -1.4449

Max Act: 0.9948. Min Act: -0.0000

Data Index: 389668 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 1.4449. Min Range: -1.4449

Max Act: 0.9812. Min Act: -0.0000

Data Index: 915253 (C4 (Web Text))

Max Activating Token Index: 167