Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 46 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.9472. Min Act: -0.1700

Data Index: 642594 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.9159. Min Act: -0.1700

Data Index: 546556 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.8847. Min Act: -0.1700

Data Index: 815500 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.8847. Min Act: -0.1700

Data Index: 703832 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.8221. Min Act: -0.1700

Data Index: 1292389 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.8534. Min Act: -0.1700

Data Index: 573429 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.8221. Min Act: -0.1700

Data Index: 676674 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.8221. Min Act: -0.1700

Data Index: 1174232 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.7908. Min Act: -0.1700

Data Index: 1315220 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.7908. Min Act: -0.1700

Data Index: 718588 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.8221. Min Act: -0.1700

Data Index: 450907 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.7908. Min Act: -0.1700

Data Index: 816909 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.7908. Min Act: -0.1700

Data Index: 1334924 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.8534. Min Act: -0.1700

Data Index: 1340703 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.7908. Min Act: -0.1700

Data Index: 839819 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.9472. Min Act: -0.1700

Data Index: 840429 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.7908. Min Act: -0.1700

Data Index: 1064157 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.7595. Min Act: -0.1700

Data Index: 530948 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.7908. Min Act: -0.1700

Data Index: 273446 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 3.9472. Min Range: -3.9472

Max Act: 3.7595. Min Act: -0.1700

Data Index: 118109 (C4 (Web Text))

Max Activating Token Index: 516