Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 265 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.0929. Min Range: -4.0929

Max Act: 4.0929. Min Act: -0.1700

Data Index: 146465 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 4.0929. Min Range: -4.0929

Max Act: 4.0304. Min Act: -0.1700

Data Index: 418033 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.9522. Min Act: -0.1700

Data Index: 1325438 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.9679. Min Act: -0.1700

Data Index: 1300177 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.9522. Min Act: -0.1700

Data Index: 317077 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.9210. Min Act: -0.1700

Data Index: 1296979 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.9053. Min Act: -0.1700

Data Index: 991782 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.9210. Min Act: -0.1700

Data Index: 116815 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.9210. Min Act: -0.1700

Data Index: 1278924 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.9210. Min Act: -0.1700

Data Index: 95503 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.8584. Min Act: -0.1700

Data Index: 769611 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.8584. Min Act: -0.1700

Data Index: 899270 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.8740. Min Act: -0.1700

Data Index: 127153 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.8115. Min Act: -0.1700

Data Index: 1161077 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.7958. Min Act: -0.1700

Data Index: 1290509 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.8428. Min Act: -0.1700

Data Index: 845095 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.8115. Min Act: -0.1700

Data Index: 1284946 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.8115. Min Act: -0.1700

Data Index: 188779 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.8428. Min Act: -0.1700

Data Index: 244265 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 4.0929. Min Range: -4.0929

Max Act: 3.8271. Min Act: -0.1700

Data Index: 964557 (C4 (Web Text))

Max Activating Token Index: 59