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

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

Neuron 1210 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.4739. Min Act: -0.1700

Data Index: 1073275 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.4425. Min Act: -0.1700

Data Index: 55374 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.4582. Min Act: -0.1700

Data Index: 591476 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.3641. Min Act: -0.1700

Data Index: 428658 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.3170. Min Act: -0.1700

Data Index: 1220878 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2542. Min Act: -0.1700

Data Index: 341241 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2385. Min Act: -0.1700

Data Index: 31685 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2542. Min Act: -0.1700

Data Index: 141942 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2385. Min Act: -0.1700

Data Index: 1119773 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2699. Min Act: -0.1700

Data Index: 506267 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2385. Min Act: -0.1700

Data Index: 182340 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2385. Min Act: -0.1700

Data Index: 600132 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2542. Min Act: -0.1700

Data Index: 1045119 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2385. Min Act: -0.1700

Data Index: 117387 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.1913. Min Act: -0.1700

Data Index: 1337051 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2070. Min Act: -0.1700

Data Index: 175284 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2070. Min Act: -0.1700

Data Index: 347259 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.1440. Min Act: -0.1700

Data Index: 1604384 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.1755. Min Act: -0.1700

Data Index: 595384 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.1598. Min Act: -0.1700

Data Index: 143 (C4 (Web Text))

Max Activating Token Index: 566