Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1513 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.5313. Min Act: -0.1700

Data Index: 245426 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.2500. Min Act: -0.1700

Data Index: 193260 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.2188. Min Act: -0.1700

Data Index: 196761 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.2188. Min Act: -0.1700

Data Index: 389402 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.1250. Min Act: -0.1700

Data Index: 798207 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.1563. Min Act: -0.1700

Data Index: 895202 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0938. Min Act: -0.1700

Data Index: 508467 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0938. Min Act: -0.1700

Data Index: 220635 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0938. Min Act: -0.1700

Data Index: 724424 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0313. Min Act: -0.1700

Data Index: 566877 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0938. Min Act: -0.1700

Data Index: 704835 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0000. Min Act: -0.1700

Data Index: 276317 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0938. Min Act: -0.1700

Data Index: 1261016 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0313. Min Act: -0.1700

Data Index: 219362 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0625. Min Act: -0.1700

Data Index: 1052358 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 5.5313. Min Range: -5.5313

Max Act: 4.9375. Min Act: -0.1700

Data Index: 808883 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0313. Min Act: -0.1700

Data Index: 776930 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0625. Min Act: -0.1700

Data Index: 8220 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 5.5313. Min Range: -5.5313

Max Act: 4.9375. Min Act: -0.1700

Data Index: 523090 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 5.5313. Min Range: -5.5313

Max Act: 5.0000. Min Act: -0.1700

Data Index: 550099 (C4 (Web Text))

Max Activating Token Index: 144