Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 300 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5105. Min Range: -5.5105

Max Act: 5.5105. Min Act: -0.1700

Data Index: 369725 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 5.5105. Min Range: -5.5105

Max Act: 5.3543. Min Act: -0.1700

Data Index: 641665 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 5.5105. Min Range: -5.5105

Max Act: 5.1043. Min Act: -0.1700

Data Index: 1094146 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.9480. Min Act: -0.1700

Data Index: 395305 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.9480. Min Act: -0.1700

Data Index: 81316 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.9168. Min Act: -0.1700

Data Index: 309228 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.8230. Min Act: -0.1700

Data Index: 1270496 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.8230. Min Act: -0.1700

Data Index: 1273860 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.7605. Min Act: -0.1700

Data Index: 755109 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.7918. Min Act: -0.1700

Data Index: 815962 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.7918. Min Act: -0.1700

Data Index: 786663 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.7605. Min Act: -0.1700

Data Index: 654944 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.7605. Min Act: -0.1700

Data Index: 1227629 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.7293. Min Act: -0.1700

Data Index: 373988 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.7293. Min Act: -0.1700

Data Index: 182189 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.7293. Min Act: -0.1700

Data Index: 1156507 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.7605. Min Act: -0.1700

Data Index: 1038526 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.7293. Min Act: -0.1700

Data Index: 793053 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.6668. Min Act: -0.1700

Data Index: 1225298 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 5.5105. Min Range: -5.5105

Max Act: 4.6980. Min Act: -0.1700

Data Index: 588195 (C4 (Web Text))

Max Activating Token Index: 116