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

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

Neuron 2023 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.5582. Min Act: -0.1700

Data Index: 371471 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.6209. Min Act: -0.1700

Data Index: 490908 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.5269. Min Act: -0.1700

Data Index: 189456 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.4329. Min Act: -0.1700

Data Index: 813300 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.4642. Min Act: -0.1700

Data Index: 1061572 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.4329. Min Act: -0.1700

Data Index: 1090808 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.4015. Min Act: -0.1700

Data Index: 206005 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.4015. Min Act: -0.1700

Data Index: 491643 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.4015. Min Act: -0.1700

Data Index: 1143642 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.4015. Min Act: -0.1700

Data Index: 830813 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.4015. Min Act: -0.1700

Data Index: 1326234 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.3701. Min Act: -0.1700

Data Index: 827782 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.3701. Min Act: -0.1700

Data Index: 11048 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.3701. Min Act: -0.1700

Data Index: 949579 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.3701. Min Act: -0.1700

Data Index: 1100108 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.3387. Min Act: -0.1700

Data Index: 221733 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.3387. Min Act: -0.1700

Data Index: 555376 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.3230. Min Act: -0.1700

Data Index: 79081 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.3230. Min Act: -0.1700

Data Index: 1316864 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 3.6209. Min Range: -3.6209

Max Act: 3.3073. Min Act: -0.1700

Data Index: 1224482 (C4 (Web Text))

Max Activating Token Index: 91