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

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

Neuron 1634 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: 3.6322. Min Range: -3.6322

Max Act: 3.6322. Min Act: -0.1700

Data Index: 1300672 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.5464. Min Act: -0.1700

Data Index: 181212 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.5286. Min Act: -0.1700

Data Index: 725603 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.5308. Min Act: -0.1700

Data Index: 301213 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.5054. Min Act: -0.1700

Data Index: 1124222 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.5113. Min Act: -0.1700

Data Index: 634498 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.4920. Min Act: -0.1700

Data Index: 506101 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.4566. Min Act: -0.1700

Data Index: 507304 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.4503. Min Act: -0.1700

Data Index: 1214342 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.4343. Min Act: -0.1700

Data Index: 1034082 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.4142. Min Act: -0.1700

Data Index: 1248502 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.4081. Min Act: -0.1700

Data Index: 379773 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.4032. Min Act: -0.1700

Data Index: 235263 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.3960. Min Act: -0.1700

Data Index: 436560 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.3879. Min Act: -0.1700

Data Index: 346317 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.3972. Min Act: -0.1700

Data Index: 156560 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.3947. Min Act: -0.1700

Data Index: 517066 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.3854. Min Act: -0.1700

Data Index: 43652 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.3804. Min Act: -0.1700

Data Index: 1100174 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 3.6322. Min Range: -3.6322

Max Act: 3.3923. Min Act: -0.1700

Data Index: 1308269 (C4 (Web Text))

Max Activating Token Index: 221