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

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

Neuron 256 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.2567. Min Act: -0.1700

Data Index: 721202 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.2096. Min Act: -0.1700

Data Index: 483599 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.1624. Min Act: -0.1700

Data Index: 1344455 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.1466. Min Act: -0.1700

Data Index: 1169617 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.1309. Min Act: -0.1700

Data Index: 484441 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.1309. Min Act: -0.1700

Data Index: 928126 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0993. Min Act: -0.1700

Data Index: 121734 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.1151. Min Act: -0.1700

Data Index: 1095119 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0836. Min Act: -0.1700

Data Index: 773479 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0836. Min Act: -0.1700

Data Index: 1108487 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0836. Min Act: -0.1700

Data Index: 753820 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0678. Min Act: -0.1700

Data Index: 928149 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0836. Min Act: -0.1700

Data Index: 1075794 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0836. Min Act: -0.1700

Data Index: 669765 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0836. Min Act: -0.1700

Data Index: 630972 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0993. Min Act: -0.1700

Data Index: 1020828 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0678. Min Act: -0.1700

Data Index: 139792 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0678. Min Act: -0.1700

Data Index: 1003 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0678. Min Act: -0.1700

Data Index: 853424 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 3.2567. Min Range: -3.2567

Max Act: 3.0678. Min Act: -0.1700

Data Index: 86675 (C4 (Web Text))

Max Activating Token Index: 337