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

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

Neuron 1630 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: 0.2967. Min Range: -0.2967

Max Act: 0.2967. Min Act: -0.0002

Data Index: 1363498 (Python Code)

Max Activating Token Index: 984

Text #1

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2837. Min Act: -0.0002

Data Index: 1390159 (Python Code)

Max Activating Token Index: 435

Text #2

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2605. Min Act: -0.0002

Data Index: 1645460 (Python Code)

Max Activating Token Index: 486

Text #3

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2725. Min Act: -0.0002

Data Index: 1518413 (Python Code)

Max Activating Token Index: 769

Text #4

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2631. Min Act: -0.0002

Data Index: 1400108 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2646. Min Act: -0.0002

Data Index: 1482900 (Python Code)

Max Activating Token Index: 312

Text #6

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2691. Min Act: -0.0002

Data Index: 1583776 (Python Code)

Max Activating Token Index: 303

Text #7

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2454. Min Act: -0.0002

Data Index: 1457954 (Python Code)

Max Activating Token Index: 407

Text #8

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2570. Min Act: -0.0002

Data Index: 1436619 (Python Code)

Max Activating Token Index: 150

Text #9

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2291. Min Act: -0.0002

Data Index: 1418921 (Python Code)

Max Activating Token Index: 340

Text #10

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2470. Min Act: -0.0002

Data Index: 1624205 (Python Code)

Max Activating Token Index: 413

Text #11

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2556. Min Act: -0.0002

Data Index: 1366444 (Python Code)

Max Activating Token Index: 879

Text #12

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2300. Min Act: -0.0002

Data Index: 1507289 (Python Code)

Max Activating Token Index: 936

Text #13

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2283. Min Act: -0.0002

Data Index: 1630860 (Python Code)

Max Activating Token Index: 875

Text #14

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2273. Min Act: -0.0002

Data Index: 1605534 (Python Code)

Max Activating Token Index: 190

Text #15

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2312. Min Act: -0.0002

Data Index: 1401449 (Python Code)

Max Activating Token Index: 345

Text #16

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2304. Min Act: -0.0002

Data Index: 1583745 (Python Code)

Max Activating Token Index: 184

Text #17

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2330. Min Act: -0.0002

Data Index: 1585494 (Python Code)

Max Activating Token Index: 465

Text #18

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2214. Min Act: -0.0002

Data Index: 1648069 (Python Code)

Max Activating Token Index: 332

Text #19

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2326. Min Act: -0.0002

Data Index: 1504727 (Python Code)

Max Activating Token Index: 100