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

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

Neuron 1785 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.7519. Min Act: -0.1700

Data Index: 601412 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.7359. Min Act: -0.1700

Data Index: 624316 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.7519. Min Act: -0.1700

Data Index: 229832 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.7199. Min Act: -0.1700

Data Index: 621829 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.7039. Min Act: -0.1700

Data Index: 588167 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6879. Min Act: -0.1700

Data Index: 112720 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6879. Min Act: -0.1700

Data Index: 179777 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6559. Min Act: -0.1700

Data Index: 948921 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6719. Min Act: -0.1700

Data Index: 654279 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6719. Min Act: -0.1700

Data Index: 1126654 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6719. Min Act: -0.1700

Data Index: 1332039 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6719. Min Act: -0.1700

Data Index: 1042788 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6559. Min Act: -0.1700

Data Index: 601486 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6559. Min Act: -0.1700

Data Index: 1179232 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6559. Min Act: -0.1700

Data Index: 1324614 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6559. Min Act: -0.1700

Data Index: 209489 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6398. Min Act: -0.1700

Data Index: 1061795 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6559. Min Act: -0.1700

Data Index: 375822 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6398. Min Act: -0.1700

Data Index: 229004 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 2.7519. Min Range: -2.7519

Max Act: 2.6398. Min Act: -0.1700

Data Index: 703916 (C4 (Web Text))

Max Activating Token Index: 1005