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

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

Neuron 221 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.6798. Min Act: -0.1700

Data Index: 510613 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.6485. Min Act: -0.1700

Data Index: 571307 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5858. Min Act: -0.1700

Data Index: 774655 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5545. Min Act: -0.1700

Data Index: 284058 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5545. Min Act: -0.1700

Data Index: 395580 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5858. Min Act: -0.1700

Data Index: 277747 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5545. Min Act: -0.1700

Data Index: 251153 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5545. Min Act: -0.1700

Data Index: 836187 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.4919. Min Act: -0.1700

Data Index: 45049 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.4919. Min Act: -0.1700

Data Index: 219423 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5232. Min Act: -0.1700

Data Index: 586532 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.4762. Min Act: -0.1700

Data Index: 448932 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.4919. Min Act: -0.1700

Data Index: 781694 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.4448. Min Act: -0.1700

Data Index: 1078807 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.4448. Min Act: -0.1700

Data Index: 941850 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.3978. Min Act: -0.1700

Data Index: 239576 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.4135. Min Act: -0.1700

Data Index: 1219213 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.4292. Min Act: -0.1700

Data Index: 69218 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.4292. Min Act: -0.1700

Data Index: 1099883 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.3978. Min Act: -0.1700

Data Index: 555776 (C4 (Web Text))

Max Activating Token Index: 293