Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 245 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.6847. Min Act: -0.1184

Data Index: 1319226 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5207. Min Act: -0.1695

Data Index: 545798 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4914. Min Act: -0.1684

Data Index: 427827 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4152. Min Act: -0.1698

Data Index: 299984 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4234. Min Act: -0.1695

Data Index: 33877 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4080. Min Act: -0.1685

Data Index: 86769 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4027. Min Act: -0.0548

Data Index: 1250777 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3875. Min Act: -0.1697

Data Index: 596047 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4023. Min Act: -0.1216

Data Index: 927924 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3739. Min Act: -0.1247

Data Index: 1103127 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3785. Min Act: -0.1697

Data Index: 417358 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3815. Min Act: -0.1697

Data Index: 788596 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3735. Min Act: -0.1607

Data Index: 788773 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3542. Min Act: -0.1690

Data Index: 55299 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3463. Min Act: -0.1700

Data Index: 1043381 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3584. Min Act: -0.1698

Data Index: 37324 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3460. Min Act: -0.1398

Data Index: 1218489 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3360. Min Act: -0.1692

Data Index: 572094 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3520. Min Act: 0.0016

Data Index: 466943 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3408. Min Act: -0.1700

Data Index: 287427 (C4 (Web Text))

Max Activating Token Index: 861