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

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

Neuron 236 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: 5.4998. Min Range: -5.4998

Max Act: 5.4998. Min Act: -0.0000

Data Index: 1255799 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 5.4998. Min Range: -5.4998

Max Act: 4.1551. Min Act: -0.0000

Data Index: 1339396 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 5.4998. Min Range: -5.4998

Max Act: 3.9251. Min Act: -0.0000

Data Index: 1085432 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 5.4998. Min Range: -5.4998

Max Act: 3.8110. Min Act: -0.0000

Data Index: 1153613 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 5.4998. Min Range: -5.4998

Max Act: 3.6404. Min Act: -0.0000

Data Index: 583578 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 5.4998. Min Range: -5.4998

Max Act: 3.6110. Min Act: -0.0000

Data Index: 1129517 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 5.4998. Min Range: -5.4998

Max Act: 3.3931. Min Act: -0.0000

Data Index: 983169 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 5.4998. Min Range: -5.4998

Max Act: 3.1527. Min Act: -0.0000

Data Index: 312506 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 5.4998. Min Range: -5.4998

Max Act: 3.1915. Min Act: -0.0000

Data Index: 725840 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 5.4998. Min Range: -5.4998

Max Act: 3.1778. Min Act: -0.0000

Data Index: 5259 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 5.4998. Min Range: -5.4998

Max Act: 3.2191. Min Act: -0.0000

Data Index: 645040 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 5.4998. Min Range: -5.4998

Max Act: 3.1714. Min Act: -0.0000

Data Index: 639150 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 5.4998. Min Range: -5.4998

Max Act: 2.8584. Min Act: -0.0000

Data Index: 211787 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 5.4998. Min Range: -5.4998

Max Act: 2.8397. Min Act: -0.0000

Data Index: 774105 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 5.4998. Min Range: -5.4998

Max Act: 2.7974. Min Act: -0.0000

Data Index: 305360 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 5.4998. Min Range: -5.4998

Max Act: 2.9354. Min Act: -0.0000

Data Index: 807761 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 5.4998. Min Range: -5.4998

Max Act: 2.8781. Min Act: -0.0000

Data Index: 135809 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 5.4998. Min Range: -5.4998

Max Act: 3.1067. Min Act: -0.0000

Data Index: 166450 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 5.4998. Min Range: -5.4998

Max Act: 2.7559. Min Act: -0.0000

Data Index: 873834 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 5.4998. Min Range: -5.4998

Max Act: 2.7537. Min Act: -0.0000

Data Index: 556081 (C4 (Web Text))

Max Activating Token Index: 90