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

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

Neuron 2212 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.5762. Min Act: -0.0001

Data Index: 72881 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.5670. Min Act: -0.0000

Data Index: 537731 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4570. Min Act: -0.0000

Data Index: 1487178 (Python Code)

Max Activating Token Index: 323

Text #3

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4900. Min Act: -0.0000

Data Index: 1263204 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.1736. Min Act: -0.0001

Data Index: 243932 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2012. Min Act: -0.0000

Data Index: 965102 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.1462. Min Act: -0.0000

Data Index: 259032 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.1345. Min Act: -0.0001

Data Index: 994175 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.1825. Min Act: -0.0000

Data Index: 1330737 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.3649. Min Act: -0.0000

Data Index: 232462 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.1621. Min Act: -0.0000

Data Index: 1077769 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2463. Min Act: -0.0000

Data Index: 209828 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1080988 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.1272. Min Act: -0.0000

Data Index: 1644229 (Python Code)

Max Activating Token Index: 390

Text #14

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2326. Min Act: -0.0000

Data Index: 1136051 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2513. Min Act: -0.0000

Data Index: 1490585 (Python Code)

Max Activating Token Index: 741

Text #16

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1236219 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.2120. Min Act: -0.0000

Data Index: 258250 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.1161. Min Act: -0.0000

Data Index: 571958 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.1945. Min Act: -0.0000

Data Index: 1210096 (C4 (Web Text))

Max Activating Token Index: 790