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

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

Neuron 487 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.4174. Min Act: -0.1700

Data Index: 759533 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.4174. Min Act: -0.1700

Data Index: 978098 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.3704. Min Act: -0.1700

Data Index: 363536 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.3233. Min Act: -0.1700

Data Index: 270705 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.3547. Min Act: -0.1700

Data Index: 485235 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.3390. Min Act: -0.1700

Data Index: 1094901 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.3390. Min Act: -0.1700

Data Index: 419209 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.3547. Min Act: -0.1700

Data Index: 1231477 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.3076. Min Act: -0.1700

Data Index: 623526 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.3390. Min Act: -0.1700

Data Index: 3509 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.2919. Min Act: -0.1700

Data Index: 299004 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.3233. Min Act: -0.1700

Data Index: 976977 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.3076. Min Act: -0.1700

Data Index: 293722 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.3076. Min Act: -0.1700

Data Index: 329366 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.2762. Min Act: -0.1700

Data Index: 1260877 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.2919. Min Act: -0.1700

Data Index: 665162 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.2919. Min Act: -0.1700

Data Index: 878778 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.2919. Min Act: -0.1700

Data Index: 1070685 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.2919. Min Act: -0.1700

Data Index: 1055988 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 3.4174. Min Range: -3.4174

Max Act: 3.2762. Min Act: -0.1700

Data Index: 509707 (C4 (Web Text))

Max Activating Token Index: 392