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

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

Neuron 1222 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: 3.3665. Min Range: -3.3665

Max Act: 3.3194. Min Act: -0.1700

Data Index: 73359 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3665. Min Act: -0.1700

Data Index: 1347708 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2880. Min Act: -0.1700

Data Index: 416785 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2880. Min Act: -0.1700

Data Index: 394688 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3037. Min Act: -0.1700

Data Index: 236503 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2722. Min Act: -0.1700

Data Index: 1259680 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3037. Min Act: -0.1700

Data Index: 645045 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2880. Min Act: -0.1700

Data Index: 1125944 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2565. Min Act: -0.1700

Data Index: 869425 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2565. Min Act: -0.1700

Data Index: 1324560 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2408. Min Act: -0.1700

Data Index: 718214 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2565. Min Act: -0.1700

Data Index: 1334705 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.1936. Min Act: -0.1700

Data Index: 1046658 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2408. Min Act: -0.1700

Data Index: 860650 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2251. Min Act: -0.1700

Data Index: 241438 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2251. Min Act: -0.1700

Data Index: 107581 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2094. Min Act: -0.1700

Data Index: 507237 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2094. Min Act: -0.1700

Data Index: 884116 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2565. Min Act: -0.1700

Data Index: 106481 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.1936. Min Act: -0.1700

Data Index: 479501 (C4 (Web Text))

Max Activating Token Index: 404