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

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

Neuron 28 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2800. Min Range: -5.2800

Max Act: 5.2800. Min Act: -0.1700

Data Index: 1343498 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 5.2800. Min Range: -5.2800

Max Act: 5.0925. Min Act: -0.1700

Data Index: 229462 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.8113. Min Act: -0.1700

Data Index: 1166930 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.7800. Min Act: -0.1700

Data Index: 1013840 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.7175. Min Act: -0.1700

Data Index: 639014 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.6550. Min Act: -0.1700

Data Index: 688284 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.6863. Min Act: -0.1700

Data Index: 926495 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.5925. Min Act: -0.1700

Data Index: 796593 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.6238. Min Act: -0.1700

Data Index: 893115 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.6550. Min Act: -0.1700

Data Index: 822054 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.5300. Min Act: -0.1700

Data Index: 1159280 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.5300. Min Act: -0.1700

Data Index: 518422 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.5925. Min Act: -0.1700

Data Index: 70696 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.5925. Min Act: -0.1700

Data Index: 1308193 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.5300. Min Act: -0.1700

Data Index: 1111011 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.5300. Min Act: -0.1700

Data Index: 638964 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.5300. Min Act: -0.1700

Data Index: 1030070 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.5300. Min Act: -0.1700

Data Index: 571675 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.5300. Min Act: -0.1700

Data Index: 1269341 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.5613. Min Act: -0.1700

Data Index: 407798 (C4 (Web Text))

Max Activating Token Index: 147