Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 68 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.1910. Min Range: -4.1910

Max Act: 4.1910. Min Act: -0.1700

Data Index: 1316614 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 4.1910. Min Range: -4.1910

Max Act: 4.0347. Min Act: -0.1700

Data Index: 1352548 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 4.1910. Min Range: -4.1910

Max Act: 4.0503. Min Act: -0.1700

Data Index: 77230 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 4.1910. Min Range: -4.1910

Max Act: 4.0034. Min Act: -0.1700

Data Index: 450874 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 4.1910. Min Range: -4.1910

Max Act: 4.0034. Min Act: -0.1700

Data Index: 417838 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.9721. Min Act: -0.1700

Data Index: 966775 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.9252. Min Act: -0.1700

Data Index: 195786 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.9096. Min Act: -0.1700

Data Index: 109296 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.9252. Min Act: -0.1700

Data Index: 117834 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.8940. Min Act: -0.1700

Data Index: 1317008 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.9096. Min Act: -0.1700

Data Index: 610531 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.9096. Min Act: -0.1700

Data Index: 832958 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.8940. Min Act: -0.1700

Data Index: 1219819 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.8940. Min Act: -0.1700

Data Index: 901042 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.8314. Min Act: -0.1700

Data Index: 876699 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.8783. Min Act: -0.1700

Data Index: 390558 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.8314. Min Act: -0.1700

Data Index: 406022 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.8470. Min Act: -0.1700

Data Index: 1302806 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.8314. Min Act: -0.1700

Data Index: 1053424 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 4.1910. Min Range: -4.1910

Max Act: 3.8158. Min Act: -0.1700

Data Index: 850354 (C4 (Web Text))

Max Activating Token Index: 302