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

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

Neuron 661 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7970. Min Act: -0.1700

Data Index: 871628 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.8283. Min Act: -0.1700

Data Index: 21315 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7970. Min Act: -0.1700

Data Index: 748298 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7814. Min Act: -0.1700

Data Index: 41025 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7501. Min Act: -0.1700

Data Index: 26544 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7657. Min Act: -0.1700

Data Index: 44247 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7501. Min Act: -0.1700

Data Index: 691022 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7657. Min Act: -0.1700

Data Index: 1189899 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7657. Min Act: -0.1700

Data Index: 823485 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7657. Min Act: -0.1700

Data Index: 894230 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7657. Min Act: -0.1700

Data Index: 342050 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7501. Min Act: -0.1700

Data Index: 1220774 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7345. Min Act: -0.1700

Data Index: 464888 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7345. Min Act: -0.1700

Data Index: 1200301 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7501. Min Act: -0.1700

Data Index: 480308 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7345. Min Act: -0.1700

Data Index: 7753 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7501. Min Act: -0.1700

Data Index: 685435 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7345. Min Act: -0.1700

Data Index: 1151417 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7501. Min Act: -0.1700

Data Index: 201257 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7188. Min Act: -0.1700

Data Index: 518202 (C4 (Web Text))

Max Activating Token Index: 391