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

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

Neuron 1393 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.3091. Min Act: -0.1700

Data Index: 1333594 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.2466. Min Act: -0.1700

Data Index: 912930 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.1841. Min Act: -0.1700

Data Index: 870263 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.1841. Min Act: -0.1700

Data Index: 841223 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.1216. Min Act: -0.1700

Data Index: 1317464 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.1216. Min Act: -0.1700

Data Index: 1198796 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.2153. Min Act: -0.1700

Data Index: 121177 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.1216. Min Act: -0.1700

Data Index: 755873 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.1841. Min Act: -0.1700

Data Index: 1049083 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.0591. Min Act: -0.1700

Data Index: 934443 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 5.3091. Min Range: -5.3091

Max Act: 4.9966. Min Act: -0.1700

Data Index: 493782 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.0591. Min Act: -0.1700

Data Index: 746575 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 5.3091. Min Range: -5.3091

Max Act: 4.9966. Min Act: -0.1700

Data Index: 797816 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 5.3091. Min Range: -5.3091

Max Act: 4.9966. Min Act: -0.1700

Data Index: 623555 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 5.3091. Min Range: -5.3091

Max Act: 4.9653. Min Act: -0.1700

Data Index: 114768 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 5.3091. Min Range: -5.3091

Max Act: 4.9966. Min Act: -0.1700

Data Index: 401500 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 5.3091. Min Range: -5.3091

Max Act: 4.9966. Min Act: -0.1700

Data Index: 512286 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.0278. Min Act: -0.1700

Data Index: 49761 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 5.3091. Min Range: -5.3091

Max Act: 4.9341. Min Act: -0.1700

Data Index: 509087 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 5.3091. Min Range: -5.3091

Max Act: 5.0278. Min Act: -0.1700

Data Index: 709690 (C4 (Web Text))

Max Activating Token Index: 707