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

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

Neuron 1516 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: 3.2118. Min Range: -3.2118

Max Act: 3.2118. Min Act: -0.1700

Data Index: 78733 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.1877. Min Act: -0.1700

Data Index: 79599 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.1859. Min Act: -0.1700

Data Index: 808595 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.1590. Min Act: -0.1700

Data Index: 305482 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.0970. Min Act: -0.1700

Data Index: 1208175 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.0754. Min Act: -0.1700

Data Index: 1359230 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9948. Min Act: -0.1700

Data Index: 469406 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9852. Min Act: -0.1700

Data Index: 242696 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9710. Min Act: -0.1700

Data Index: 1335886 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9229. Min Act: -0.1700

Data Index: 1143981 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8993. Min Act: -0.1700

Data Index: 1561301 (Python Code)

Max Activating Token Index: 206

Text #11

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8929. Min Act: -0.1700

Data Index: 44122 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8975. Min Act: -0.1700

Data Index: 954810 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8707. Min Act: -0.1696

Data Index: 164449 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8557. Min Act: -0.1700

Data Index: 1095430 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8608. Min Act: -0.1700

Data Index: 1219987 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8396. Min Act: -0.1699

Data Index: 112750 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8565. Min Act: -0.1700

Data Index: 1314817 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8232. Min Act: -0.1699

Data Index: 272058 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8319. Min Act: -0.1700

Data Index: 1131169 (C4 (Web Text))

Max Activating Token Index: 194