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

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

Neuron 1409 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.5190. Min Act: -0.1700

Data Index: 679127 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.4719. Min Act: -0.1700

Data Index: 891079 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.4719. Min Act: -0.1700

Data Index: 923317 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.4249. Min Act: -0.1700

Data Index: 1325339 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3935. Min Act: -0.1700

Data Index: 714192 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.4092. Min Act: -0.1700

Data Index: 858908 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.4092. Min Act: -0.1700

Data Index: 510404 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3622. Min Act: -0.1700

Data Index: 853534 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3622. Min Act: -0.1700

Data Index: 832567 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3465. Min Act: -0.1700

Data Index: 127213 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3465. Min Act: -0.1700

Data Index: 839708 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3465. Min Act: -0.1700

Data Index: 1068624 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3308. Min Act: -0.1700

Data Index: 557449 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3151. Min Act: -0.1700

Data Index: 170504 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.2994. Min Act: -0.1700

Data Index: 969135 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3308. Min Act: -0.1700

Data Index: 110616 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3465. Min Act: -0.1700

Data Index: 1334147 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3308. Min Act: -0.1700

Data Index: 1956 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.3465. Min Act: -0.1700

Data Index: 970029 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 3.5190. Min Range: -3.5190

Max Act: 3.2994. Min Act: -0.1700

Data Index: 318460 (C4 (Web Text))

Max Activating Token Index: 263