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

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

Neuron 1128 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.9172. Min Act: -0.1700

Data Index: 592453 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.8546. Min Act: -0.1700

Data Index: 1003093 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.8546. Min Act: -0.1700

Data Index: 65872 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.8390. Min Act: -0.1700

Data Index: 1190570 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.8234. Min Act: -0.1700

Data Index: 775610 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.8234. Min Act: -0.1700

Data Index: 492296 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7921. Min Act: -0.1700

Data Index: 1309167 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7764. Min Act: -0.1700

Data Index: 687434 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7608. Min Act: -0.1700

Data Index: 954093 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7764. Min Act: -0.1700

Data Index: 1029561 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7608. Min Act: -0.1700

Data Index: 1018792 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7608. Min Act: -0.1700

Data Index: 1012550 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7764. Min Act: -0.1700

Data Index: 760031 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7452. Min Act: -0.1700

Data Index: 788948 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7452. Min Act: -0.1700

Data Index: 960175 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7295. Min Act: -0.1700

Data Index: 553735 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7295. Min Act: -0.1700

Data Index: 123260 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7295. Min Act: -0.1700

Data Index: 711055 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.6982. Min Act: -0.1700

Data Index: 964596 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 3.9172. Min Range: -3.9172

Max Act: 3.7452. Min Act: -0.1700

Data Index: 127878 (C4 (Web Text))

Max Activating Token Index: 387