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

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

Neuron 1228 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: 4.3917. Min Range: -4.3917

Max Act: 4.3917. Min Act: -0.1700

Data Index: 422234 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.2561. Min Act: -0.1700

Data Index: 228490 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.2236. Min Act: -0.1700

Data Index: 345584 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.1903. Min Act: -0.1700

Data Index: 1555513 (Python Code)

Max Activating Token Index: 88

Text #4

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.1796. Min Act: -0.1700

Data Index: 756453 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.1435. Min Act: -0.1700

Data Index: 895163 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.1353. Min Act: -0.1700

Data Index: 41373 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.1282. Min Act: -0.1700

Data Index: 82954 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.1253. Min Act: -0.1700

Data Index: 507859 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.1352. Min Act: -0.1700

Data Index: 1261456 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.0936. Min Act: -0.1700

Data Index: 1160376 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.1418. Min Act: -0.1700

Data Index: 278329 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.1084. Min Act: -0.1700

Data Index: 19152 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.1044. Min Act: -0.1700

Data Index: 790178 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.0519. Min Act: -0.1700

Data Index: 314902 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.0222. Min Act: -0.1700

Data Index: 293081 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.0195. Min Act: -0.1700

Data Index: 995117 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.0392. Min Act: -0.1700

Data Index: 785296 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.0319. Min Act: -0.1700

Data Index: 1651513 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 4.3917. Min Range: -4.3917

Max Act: 4.0251. Min Act: -0.1700

Data Index: 116608 (C4 (Web Text))

Max Activating Token Index: 252