Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1037 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.2126. Min Range: -4.2126

Max Act: 4.2126. Min Act: -0.1700

Data Index: 378962 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 4.2126. Min Range: -4.2126

Max Act: 4.1571. Min Act: -0.1700

Data Index: 936765 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 4.2126. Min Range: -4.2126

Max Act: 4.1330. Min Act: -0.1700

Data Index: 82150 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 4.2126. Min Range: -4.2126

Max Act: 4.1391. Min Act: -0.1700

Data Index: 880081 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 4.2126. Min Range: -4.2126

Max Act: 4.0574. Min Act: -0.1700

Data Index: 1303047 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9944. Min Act: -0.1700

Data Index: 633177 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 4.2126. Min Range: -4.2126

Max Act: 4.0195. Min Act: -0.1700

Data Index: 593280 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 4.2126. Min Range: -4.2126

Max Act: 4.0044. Min Act: -0.1700

Data Index: 1412002 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9982. Min Act: -0.1700

Data Index: 956735 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9738. Min Act: -0.1700

Data Index: 1169739 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9981. Min Act: -0.1700

Data Index: 242546 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9733. Min Act: -0.1700

Data Index: 215969 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9970. Min Act: -0.1700

Data Index: 588772 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9769. Min Act: -0.1700

Data Index: 458020 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9494. Min Act: -0.1700

Data Index: 423300 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9980. Min Act: -0.1700

Data Index: 1649343 (Python Code)

Max Activating Token Index: 593

Text #16

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9802. Min Act: -0.1700

Data Index: 187316 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9339. Min Act: -0.1700

Data Index: 270873 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9211. Min Act: -0.1700

Data Index: 39110 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 4.2126. Min Range: -4.2126

Max Act: 3.9425. Min Act: -0.1700

Data Index: 759035 (C4 (Web Text))

Max Activating Token Index: 21