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

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

Neuron 1855 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: 5.1493. Min Range: -5.1493

Max Act: 5.1493. Min Act: -0.1700

Data Index: 196588 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 5.1493. Min Range: -5.1493

Max Act: 5.0868. Min Act: -0.1700

Data Index: 1288544 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 5.1493. Min Range: -5.1493

Max Act: 5.0868. Min Act: -0.1700

Data Index: 1161937 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 5.1493. Min Range: -5.1493

Max Act: 5.0243. Min Act: -0.1700

Data Index: 1041314 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 5.1493. Min Range: -5.1493

Max Act: 5.0243. Min Act: -0.1700

Data Index: 1247768 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 5.1493. Min Range: -5.1493

Max Act: 5.0555. Min Act: -0.1700

Data Index: 39834 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9930. Min Act: -0.1700

Data Index: 117922 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9930. Min Act: -0.1700

Data Index: 411680 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9305. Min Act: -0.1700

Data Index: 944339 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9618. Min Act: -0.1700

Data Index: 618972 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9305. Min Act: -0.1700

Data Index: 1333835 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9305. Min Act: -0.1700

Data Index: 812522 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.8993. Min Act: -0.1700

Data Index: 313056 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9305. Min Act: -0.1700

Data Index: 850780 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9305. Min Act: -0.1700

Data Index: 362841 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.8993. Min Act: -0.1700

Data Index: 933779 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.8993. Min Act: -0.1700

Data Index: 187113 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.8993. Min Act: -0.1700

Data Index: 383186 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.8993. Min Act: -0.1700

Data Index: 267896 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.8368. Min Act: -0.1700

Data Index: 1017605 (C4 (Web Text))

Max Activating Token Index: 338