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

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

Neuron 1889 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: 5.7423. Min Range: -5.7423

Max Act: 5.7423. Min Act: -0.1700

Data Index: 891182 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 5.7423. Min Range: -5.7423

Max Act: 5.2423. Min Act: -0.1700

Data Index: 1393919 (Python Code)

Max Activating Token Index: 832

Text #2

Max Range: 5.7423. Min Range: -5.7423

Max Act: 5.1329. Min Act: -0.1700

Data Index: 297552 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 5.7423. Min Range: -5.7423

Max Act: 5.1016. Min Act: -0.1700

Data Index: 543157 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 5.7423. Min Range: -5.7423

Max Act: 5.0391. Min Act: -0.1700

Data Index: 787955 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 5.7423. Min Range: -5.7423

Max Act: 5.0391. Min Act: -0.1700

Data Index: 68205 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 5.7423. Min Range: -5.7423

Max Act: 5.0079. Min Act: -0.1700

Data Index: 94268 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.9923. Min Act: -0.1700

Data Index: 1095459 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 5.7423. Min Range: -5.7423

Max Act: 5.0391. Min Act: -0.1700

Data Index: 687360 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.9923. Min Act: -0.1700

Data Index: 1116913 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.8673. Min Act: -0.1700

Data Index: 1115054 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.8985. Min Act: -0.1700

Data Index: 1123572 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.7891. Min Act: -0.1700

Data Index: 1468281 (Python Code)

Max Activating Token Index: 94

Text #13

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.8048. Min Act: -0.1700

Data Index: 1398365 (Python Code)

Max Activating Token Index: 892

Text #14

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.7579. Min Act: -0.1700

Data Index: 630495 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.7266. Min Act: -0.1700

Data Index: 641557 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.7579. Min Act: -0.1700

Data Index: 996941 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.7423. Min Act: -0.1700

Data Index: 1516602 (Python Code)

Max Activating Token Index: 984

Text #18

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.7735. Min Act: -0.1700

Data Index: 349787 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 5.7423. Min Range: -5.7423

Max Act: 4.7423. Min Act: -0.1700

Data Index: 310218 (C4 (Web Text))

Max Activating Token Index: 553