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

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

Neuron 1002 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: 3.6883. Min Range: -3.6883

Max Act: 3.6883. Min Act: -0.1700

Data Index: 95524 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.6883. Min Act: -0.1700

Data Index: 1353832 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.6883. Min Act: -0.1700

Data Index: 975608 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.6883. Min Act: -0.1700

Data Index: 428116 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.6883. Min Act: -0.1700

Data Index: 105898 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.6570. Min Act: -0.1700

Data Index: 510119 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.6570. Min Act: -0.1700

Data Index: 1097058 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.6883. Min Act: -0.1700

Data Index: 1148800 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5944. Min Act: -0.1700

Data Index: 110885 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.6257. Min Act: -0.1700

Data Index: 1164894 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5944. Min Act: -0.1700

Data Index: 1082487 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.6257. Min Act: -0.1700

Data Index: 946121 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5944. Min Act: -0.1700

Data Index: 345332 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5630. Min Act: -0.1700

Data Index: 62272 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5474. Min Act: -0.1700

Data Index: 1327025 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5317. Min Act: -0.1700

Data Index: 681200 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5474. Min Act: -0.1700

Data Index: 983340 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5160. Min Act: -0.1700

Data Index: 53723 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5004. Min Act: -0.1700

Data Index: 194199 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5317. Min Act: -0.1700

Data Index: 42487 (C4 (Web Text))

Max Activating Token Index: 63