Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 393 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.4344. Min Act: -0.1700

Data Index: 443863 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3717. Min Act: -0.1700

Data Index: 1039423 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.2617. Min Act: -0.1700

Data Index: 148541 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.2303. Min Act: -0.1700

Data Index: 382063 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.1988. Min Act: -0.1700

Data Index: 1035003 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.1674. Min Act: -0.1700

Data Index: 81278 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.1674. Min Act: -0.1700

Data Index: 78749 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.1359. Min Act: -0.1700

Data Index: 834403 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.0570. Min Act: -0.1700

Data Index: 1101549 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.0412. Min Act: -0.1700

Data Index: 130366 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.0254. Min Act: -0.1700

Data Index: 986728 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.0254. Min Act: -0.1700

Data Index: 487518 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 3.4344. Min Range: -3.4344

Max Act: 2.9780. Min Act: -0.1700

Data Index: 770045 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 3.4344. Min Range: -3.4344

Max Act: 2.9938. Min Act: -0.1700

Data Index: 1193302 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 3.4344. Min Range: -3.4344

Max Act: 2.9464. Min Act: -0.1700

Data Index: 1250287 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 3.4344. Min Range: -3.4344

Max Act: 2.9305. Min Act: -0.1700

Data Index: 863820 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 3.4344. Min Range: -3.4344

Max Act: 2.9464. Min Act: -0.1700

Data Index: 1088705 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 3.4344. Min Range: -3.4344

Max Act: 2.9464. Min Act: -0.1700

Data Index: 1332054 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 3.4344. Min Range: -3.4344

Max Act: 2.9622. Min Act: -0.1700

Data Index: 1283111 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 3.4344. Min Range: -3.4344

Max Act: 2.9147. Min Act: -0.1700

Data Index: 1330412 (C4 (Web Text))

Max Activating Token Index: 991