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

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

Neuron 996 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: 5.0335. Min Range: -5.0335

Max Act: 5.0335. Min Act: -0.1700

Data Index: 1076531 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.9085. Min Act: -0.1700

Data Index: 116351 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8773. Min Act: -0.1700

Data Index: 480815 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8773. Min Act: -0.1700

Data Index: 169436 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8773. Min Act: -0.1700

Data Index: 1208794 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8460. Min Act: -0.1700

Data Index: 1172315 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8460. Min Act: -0.1700

Data Index: 1530831 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8460. Min Act: -0.1700

Data Index: 44426 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.7210. Min Act: -0.1700

Data Index: 905155 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8148. Min Act: -0.1700

Data Index: 760788 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8148. Min Act: -0.1700

Data Index: 965928 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8148. Min Act: -0.1700

Data Index: 265743 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8148. Min Act: -0.1700

Data Index: 827888 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.7835. Min Act: -0.1700

Data Index: 539030 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8148. Min Act: -0.1700

Data Index: 437387 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.8148. Min Act: -0.1700

Data Index: 949800 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.7523. Min Act: -0.1700

Data Index: 832915 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.7523. Min Act: -0.1700

Data Index: 912490 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.7210. Min Act: -0.1700

Data Index: 925153 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 5.0335. Min Range: -5.0335

Max Act: 4.7210. Min Act: -0.1700

Data Index: 704606 (C4 (Web Text))

Max Activating Token Index: 960