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

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

Neuron 788 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: 3.5705. Min Range: -3.5705

Max Act: 3.5705. Min Act: -0.1664

Data Index: 1339693 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.5660. Min Act: -0.1680

Data Index: 1121754 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.5364. Min Act: -0.1700

Data Index: 732718 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.4995. Min Act: -0.1651

Data Index: 1221166 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.4364. Min Act: -0.1699

Data Index: 680674 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.4273. Min Act: -0.1699

Data Index: 1219137 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3969. Min Act: -0.1700

Data Index: 281547 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3853. Min Act: -0.1680

Data Index: 663672 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3880. Min Act: -0.1700

Data Index: 914420 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3403. Min Act: -0.1700

Data Index: 1067807 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3336. Min Act: -0.1700

Data Index: 160683 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3533. Min Act: -0.1700

Data Index: 1047708 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3521. Min Act: -0.1693

Data Index: 343339 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3527. Min Act: -0.1700

Data Index: 264386 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3615. Min Act: -0.1700

Data Index: 1084950 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3407. Min Act: -0.1699

Data Index: 957098 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3164. Min Act: -0.1699

Data Index: 232431 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3107. Min Act: -0.1624

Data Index: 1139730 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.3392. Min Act: -0.1700

Data Index: 228064 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 3.5705. Min Range: -3.5705

Max Act: 3.2985. Min Act: -0.1699

Data Index: 570282 (C4 (Web Text))

Max Activating Token Index: 557