Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1507 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.7314. Min Act: -0.1700

Data Index: 916921 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.6062. Min Act: -0.1700

Data Index: 821529 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.6062. Min Act: -0.1700

Data Index: 504527 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.6218. Min Act: -0.1700

Data Index: 1289332 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4495. Min Act: -0.1700

Data Index: 760236 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4965. Min Act: -0.1700

Data Index: 2128 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4338. Min Act: -0.1700

Data Index: 1451901 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4652. Min Act: -0.1700

Data Index: 686013 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4338. Min Act: -0.1700

Data Index: 1136954 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4652. Min Act: -0.1700

Data Index: 1123246 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4182. Min Act: -0.1700

Data Index: 1577106 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4495. Min Act: -0.1700

Data Index: 372640 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4182. Min Act: -0.1700

Data Index: 111607 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4338. Min Act: -0.1700

Data Index: 526487 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4652. Min Act: -0.1700

Data Index: 28061 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4338. Min Act: -0.1700

Data Index: 1345438 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4338. Min Act: -0.1700

Data Index: 734361 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4025. Min Act: -0.1700

Data Index: 438724 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.4338. Min Act: -0.1700

Data Index: 1090775 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 3.7314. Min Range: -3.7314

Max Act: 3.3868. Min Act: -0.1700

Data Index: 1222421 (C4 (Web Text))

Max Activating Token Index: 755