Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1255 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2770. Min Act: -0.0002

Data Index: 1649523 (Python Code)

Max Activating Token Index: 187

Text #1

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2664. Min Act: -0.0002

Data Index: 1511594 (Python Code)

Max Activating Token Index: 97

Text #2

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2551. Min Act: -0.0002

Data Index: 1519899 (Python Code)

Max Activating Token Index: 164

Text #3

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2524. Min Act: -0.0002

Data Index: 1487499 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2439. Min Act: -0.0002

Data Index: 1446053 (Python Code)

Max Activating Token Index: 185

Text #5

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2542. Min Act: -0.0002

Data Index: 1646476 (Python Code)

Max Activating Token Index: 183

Text #6

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1541658 (Python Code)

Max Activating Token Index: 761

Text #7

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2575. Min Act: -0.0002

Data Index: 1565118 (Python Code)

Max Activating Token Index: 833

Text #8

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2526. Min Act: -0.0002

Data Index: 1441172 (Python Code)

Max Activating Token Index: 788

Text #9

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2411. Min Act: -0.0002

Data Index: 1632172 (Python Code)

Max Activating Token Index: 806

Text #10

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2369. Min Act: -0.0002

Data Index: 1399261 (Python Code)

Max Activating Token Index: 818

Text #11

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2366. Min Act: -0.0002

Data Index: 1647234 (Python Code)

Max Activating Token Index: 649

Text #12

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2437. Min Act: -0.0002

Data Index: 1484286 (Python Code)

Max Activating Token Index: 673

Text #13

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2343. Min Act: -0.0002

Data Index: 1614219 (Python Code)

Max Activating Token Index: 372

Text #14

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2322. Min Act: -0.0002

Data Index: 1543691 (Python Code)

Max Activating Token Index: 384

Text #15

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2198. Min Act: -0.0002

Data Index: 1417284 (Python Code)

Max Activating Token Index: 332

Text #16

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2248. Min Act: -0.0002

Data Index: 1414754 (Python Code)

Max Activating Token Index: 990

Text #17

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2319. Min Act: -0.0002

Data Index: 1573702 (Python Code)

Max Activating Token Index: 57

Text #18

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2234. Min Act: -0.0002

Data Index: 1656756 (Python Code)

Max Activating Token Index: 136

Text #19

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2309. Min Act: -0.0002

Data Index: 1625764 (Python Code)

Max Activating Token Index: 597