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

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

Neuron 1588 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: 5.3510. Min Range: -5.3510

Max Act: 5.3510. Min Act: -0.1700

Data Index: 412165 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 5.3510. Min Range: -5.3510

Max Act: 5.1948. Min Act: -0.1700

Data Index: 1329332 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 5.3510. Min Range: -5.3510

Max Act: 5.1323. Min Act: -0.1700

Data Index: 1140328 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 5.3510. Min Range: -5.3510

Max Act: 5.1635. Min Act: -0.1700

Data Index: 591418 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 5.3510. Min Range: -5.3510

Max Act: 5.1010. Min Act: -0.1700

Data Index: 832275 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 5.3510. Min Range: -5.3510

Max Act: 5.0385. Min Act: -0.1700

Data Index: 990518 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 5.3510. Min Range: -5.3510

Max Act: 5.0385. Min Act: -0.1700

Data Index: 1332799 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 5.3510. Min Range: -5.3510

Max Act: 5.0698. Min Act: -0.1700

Data Index: 212394 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.9760. Min Act: -0.1700

Data Index: 389701 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.8198. Min Act: -0.1700

Data Index: 949428 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.9135. Min Act: -0.1700

Data Index: 550756 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.8198. Min Act: -0.1700

Data Index: 387197 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.9448. Min Act: -0.1700

Data Index: 581773 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.8198. Min Act: -0.1700

Data Index: 212873 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.7573. Min Act: -0.1700

Data Index: 1139452 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.8510. Min Act: -0.1700

Data Index: 524777 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.7885. Min Act: -0.1700

Data Index: 1045685 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.6635. Min Act: -0.1700

Data Index: 653259 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.7573. Min Act: -0.1700

Data Index: 519701 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 5.3510. Min Range: -5.3510

Max Act: 4.6322. Min Act: -0.1700

Data Index: 569050 (C4 (Web Text))

Max Activating Token Index: 526