Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1706 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.5553. Min Act: -0.1700

Data Index: 883952 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.5084. Min Act: -0.1700

Data Index: 1165236 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.3365. Min Act: -0.1700

Data Index: 1304207 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.3678. Min Act: -0.1700

Data Index: 1192783 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.3365. Min Act: -0.1700

Data Index: 1146805 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.3053. Min Act: -0.1700

Data Index: 1621647 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.2428. Min Act: -0.1700

Data Index: 430303 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.2584. Min Act: -0.1700

Data Index: 450874 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.3209. Min Act: -0.1700

Data Index: 447521 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.2428. Min Act: -0.1700

Data Index: 984926 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.2584. Min Act: -0.1700

Data Index: 963164 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.1803. Min Act: -0.1700

Data Index: 677414 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.2584. Min Act: -0.1700

Data Index: 1610220 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.1646. Min Act: -0.1700

Data Index: 301464 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.2428. Min Act: -0.1700

Data Index: 1316614 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.2115. Min Act: -0.1700

Data Index: 1280708 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.1959. Min Act: -0.1700

Data Index: 603543 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.1646. Min Act: -0.1700

Data Index: 1367386 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.2428. Min Act: -0.1700

Data Index: 1642732 (Python Code)

Max Activating Token Index: 153

Text #19

Max Range: 5.5553. Min Range: -5.5553

Max Act: 5.2115. Min Act: -0.1700

Data Index: 410597 (C4 (Web Text))

Max Activating Token Index: 623