Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 384 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.7117. Min Act: -0.1700

Data Index: 603386 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.6727. Min Act: -0.1690

Data Index: 569948 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.6910. Min Act: -0.1700

Data Index: 1338075 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.6246. Min Act: -0.1700

Data Index: 261205 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.6111. Min Act: -0.1700

Data Index: 1292402 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5892. Min Act: -0.1699

Data Index: 459512 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5811. Min Act: -0.1700

Data Index: 46319 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5896. Min Act: -0.1700

Data Index: 626 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5763. Min Act: -0.1700

Data Index: 721335 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5463. Min Act: -0.1700

Data Index: 487864 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5468. Min Act: -0.1700

Data Index: 526665 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5409. Min Act: -0.1700

Data Index: 144320 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5223. Min Act: -0.1700

Data Index: 1580715 (Python Code)

Max Activating Token Index: 679

Text #13

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5206. Min Act: -0.1700

Data Index: 150613 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5140. Min Act: -0.1700

Data Index: 369451 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5267. Min Act: -0.1700

Data Index: 567403 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5391. Min Act: -0.1698

Data Index: 1158691 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5264. Min Act: -0.1700

Data Index: 912833 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.4825. Min Act: -0.1700

Data Index: 645600 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.4948. Min Act: -0.1700

Data Index: 982413 (C4 (Web Text))

Max Activating Token Index: 556