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

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

Neuron 2003 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: 0.2965. Min Range: -0.2965

Max Act: 0.2965. Min Act: -0.0002

Data Index: 1562185 (Python Code)

Max Activating Token Index: 238

Text #1

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2797. Min Act: -0.0002

Data Index: 1603844 (Python Code)

Max Activating Token Index: 401

Text #2

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2684. Min Act: -0.0002

Data Index: 1406356 (Python Code)

Max Activating Token Index: 399

Text #3

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2541. Min Act: -0.0002

Data Index: 1438881 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2527. Min Act: -0.0002

Data Index: 1500378 (Python Code)

Max Activating Token Index: 450

Text #5

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2605. Min Act: -0.0002

Data Index: 1380111 (Python Code)

Max Activating Token Index: 819

Text #6

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2541. Min Act: -0.0002

Data Index: 1426176 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2642. Min Act: -0.0002

Data Index: 1412298 (Python Code)

Max Activating Token Index: 981

Text #8

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2490. Min Act: -0.0002

Data Index: 1605499 (Python Code)

Max Activating Token Index: 966

Text #9

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2413. Min Act: -0.0002

Data Index: 1573138 (Python Code)

Max Activating Token Index: 580

Text #10

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2711. Min Act: -0.0002

Data Index: 1455128 (Python Code)

Max Activating Token Index: 917

Text #11

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2389. Min Act: -0.0002

Data Index: 1635092 (Python Code)

Max Activating Token Index: 424

Text #12

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2546. Min Act: -0.0002

Data Index: 1436219 (Python Code)

Max Activating Token Index: 978

Text #13

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2470. Min Act: -0.0002

Data Index: 1522203 (Python Code)

Max Activating Token Index: 753

Text #14

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2443. Min Act: -0.0002

Data Index: 1377241 (Python Code)

Max Activating Token Index: 373

Text #15

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2405. Min Act: -0.0002

Data Index: 1446893 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2312. Min Act: -0.0002

Data Index: 1646707 (Python Code)

Max Activating Token Index: 668

Text #17

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2413. Min Act: -0.0002

Data Index: 1482289 (Python Code)

Max Activating Token Index: 411

Text #18

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2431. Min Act: -0.0002

Data Index: 1360608 (Python Code)

Max Activating Token Index: 180

Text #19

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2267. Min Act: -0.0002

Data Index: 1546902 (Python Code)

Max Activating Token Index: 1003