Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1446 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.6431. Min Act: -0.1700

Data Index: 1365976 (Python Code)

Max Activating Token Index: 599

Text #1

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.4378. Min Act: -0.1700

Data Index: 1396354 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.3762. Min Act: -0.1700

Data Index: 1556816 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.3456. Min Act: -0.1700

Data Index: 1506637 (Python Code)

Max Activating Token Index: 69

Text #4

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.3000. Min Act: -0.1700

Data Index: 1632252 (Python Code)

Max Activating Token Index: 673

Text #5

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.2934. Min Act: -0.1700

Data Index: 1613520 (Python Code)

Max Activating Token Index: 528

Text #6

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.3083. Min Act: -0.1700

Data Index: 1369957 (Python Code)

Max Activating Token Index: 468

Text #7

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.2968. Min Act: -0.1700

Data Index: 1631464 (Python Code)

Max Activating Token Index: 236

Text #8

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.2749. Min Act: -0.1700

Data Index: 1364313 (Python Code)

Max Activating Token Index: 133

Text #9

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.2114. Min Act: -0.1700

Data Index: 1474615 (Python Code)

Max Activating Token Index: 595

Text #10

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.2178. Min Act: -0.1700

Data Index: 1382904 (Python Code)

Max Activating Token Index: 510

Text #11

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.2360. Min Act: -0.1700

Data Index: 1578958 (Python Code)

Max Activating Token Index: 476

Text #12

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.1915. Min Act: -0.1700

Data Index: 1457772 (Python Code)

Max Activating Token Index: 1005

Text #13

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.1966. Min Act: -0.1700

Data Index: 1550549 (Python Code)

Max Activating Token Index: 769

Text #14

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.1972. Min Act: -0.1700

Data Index: 1404728 (Python Code)

Max Activating Token Index: 842

Text #15

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.1839. Min Act: -0.1700

Data Index: 1547091 (Python Code)

Max Activating Token Index: 461

Text #16

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.2044. Min Act: -0.1700

Data Index: 1642430 (Python Code)

Max Activating Token Index: 250

Text #17

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.1566. Min Act: -0.1700

Data Index: 1360449 (Python Code)

Max Activating Token Index: 827

Text #18

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.1767. Min Act: -0.1700

Data Index: 1507364 (Python Code)

Max Activating Token Index: 103

Text #19

Max Range: 4.6431. Min Range: -4.6431

Max Act: 4.1775. Min Act: -0.1700

Data Index: 1384553 (Python Code)

Max Activating Token Index: 970