Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1830 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.9229. Min Act: -0.1700

Data Index: 244861 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.8916. Min Act: -0.1700

Data Index: 434502 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.8916. Min Act: -0.1700

Data Index: 893589 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.8604. Min Act: -0.1700

Data Index: 376754 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.8291. Min Act: -0.1700

Data Index: 1149836 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7665. Min Act: -0.1700

Data Index: 290454 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.8291. Min Act: -0.1700

Data Index: 635452 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7352. Min Act: -0.1700

Data Index: 186530 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7978. Min Act: -0.1700

Data Index: 102035 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7665. Min Act: -0.1700

Data Index: 686049 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7978. Min Act: -0.1700

Data Index: 1306507 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7978. Min Act: -0.1700

Data Index: 665548 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7665. Min Act: -0.1700

Data Index: 191592 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7665. Min Act: -0.1700

Data Index: 206232 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7665. Min Act: -0.1700

Data Index: 984656 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7352. Min Act: -0.1700

Data Index: 73166 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7039. Min Act: -0.1700

Data Index: 893202 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7352. Min Act: -0.1700

Data Index: 1143660 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7039. Min Act: -0.1700

Data Index: 1012426 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 3.9229. Min Range: -3.9229

Max Act: 3.7665. Min Act: -0.1700

Data Index: 97805 (C4 (Web Text))

Max Activating Token Index: 414