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

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

Neuron 270 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: 3.8304. Min Range: -3.8304

Max Act: 3.8304. Min Act: -0.1700

Data Index: 211551 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.8304. Min Act: -0.1700

Data Index: 391914 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7991. Min Act: -0.1700

Data Index: 845492 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.8304. Min Act: -0.1700

Data Index: 380455 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7991. Min Act: -0.1700

Data Index: 1085126 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7366. Min Act: -0.1700

Data Index: 451583 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7366. Min Act: -0.1700

Data Index: 277428 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7679. Min Act: -0.1700

Data Index: 457431 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7679. Min Act: -0.1700

Data Index: 762408 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7522. Min Act: -0.1700

Data Index: 1208088 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7522. Min Act: -0.1700

Data Index: 1097395 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7366. Min Act: -0.1700

Data Index: 160230 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7366. Min Act: -0.1700

Data Index: 652349 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7366. Min Act: -0.1700

Data Index: 1172763 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7366. Min Act: -0.1700

Data Index: 487994 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7209. Min Act: -0.1700

Data Index: 1075875 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7209. Min Act: -0.1700

Data Index: 731635 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7522. Min Act: -0.1700

Data Index: 478934 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7366. Min Act: -0.1700

Data Index: 876057 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 3.8304. Min Range: -3.8304

Max Act: 3.7209. Min Act: -0.1700

Data Index: 687262 (C4 (Web Text))

Max Activating Token Index: 52