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

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

Neuron 197 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.6706. Min Act: -0.1700

Data Index: 509089 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.5768. Min Act: -0.1700

Data Index: 664035 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.3893. Min Act: -0.1699

Data Index: 1154555 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.2956. Min Act: -0.1700

Data Index: 517792 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.3268. Min Act: -0.1700

Data Index: 1189445 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.2956. Min Act: -0.1695

Data Index: 525650 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.2018. Min Act: -0.1700

Data Index: 1285328 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.1393. Min Act: -0.1700

Data Index: 774534 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.1081. Min Act: -0.1699

Data Index: 210539 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.1081. Min Act: -0.1700

Data Index: 574502 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.0768. Min Act: -0.1700

Data Index: 1285346 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.0456. Min Act: -0.1700

Data Index: 748313 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.0143. Min Act: -0.1700

Data Index: 139891 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.0143. Min Act: -0.1700

Data Index: 1242559 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.0143. Min Act: -0.1700

Data Index: 1286281 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.9518. Min Act: -0.1696

Data Index: 693620 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.0456. Min Act: -0.1700

Data Index: 326835 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.0143. Min Act: -0.1700

Data Index: 253478 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.0143. Min Act: -0.1700

Data Index: 1340513 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.9831. Min Act: -0.1700

Data Index: 256199 (C4 (Web Text))

Max Activating Token Index: 782