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

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

Neuron 975 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: 3.8485. Min Range: -3.8485

Max Act: 3.8016. Min Act: -0.1700

Data Index: 777379 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.8485. Min Act: -0.1700

Data Index: 249186 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.8329. Min Act: -0.1700

Data Index: 1210706 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.7703. Min Act: -0.1700

Data Index: 1164785 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.7390. Min Act: -0.1700

Data Index: 367423 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.7547. Min Act: -0.1700

Data Index: 595158 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.6921. Min Act: -0.1700

Data Index: 301841 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.7078. Min Act: -0.1700

Data Index: 1079312 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.6765. Min Act: -0.1700

Data Index: 1051518 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.6608. Min Act: -0.1700

Data Index: 509719 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.7078. Min Act: -0.1700

Data Index: 991708 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.7078. Min Act: -0.1700

Data Index: 921116 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.6608. Min Act: -0.1700

Data Index: 326582 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.6765. Min Act: -0.1700

Data Index: 425578 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.6452. Min Act: -0.1700

Data Index: 888213 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.6765. Min Act: -0.1700

Data Index: 1110261 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.5982. Min Act: -0.1700

Data Index: 956400 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.6921. Min Act: -0.1700

Data Index: 918650 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.6295. Min Act: -0.1700

Data Index: 294402 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 3.8485. Min Range: -3.8485

Max Act: 3.6138. Min Act: -0.1700

Data Index: 1173148 (C4 (Web Text))

Max Activating Token Index: 540