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

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

Neuron 1646 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: 3.5175. Min Range: -3.5175

Max Act: 3.5175. Min Act: -0.1700

Data Index: 567888 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.4862. Min Act: -0.1700

Data Index: 198143 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.4548. Min Act: -0.1700

Data Index: 695889 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.4078. Min Act: -0.1700

Data Index: 536991 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3921. Min Act: -0.1700

Data Index: 152308 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.4078. Min Act: -0.1700

Data Index: 741387 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3764. Min Act: -0.1700

Data Index: 1168693 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.4078. Min Act: -0.1700

Data Index: 134322 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.4078. Min Act: -0.1700

Data Index: 232192 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3607. Min Act: -0.1700

Data Index: 645278 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3764. Min Act: -0.1700

Data Index: 1298883 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3764. Min Act: -0.1700

Data Index: 863910 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3764. Min Act: -0.1700

Data Index: 1239705 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3607. Min Act: -0.1700

Data Index: 407755 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3450. Min Act: -0.1700

Data Index: 77044 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3607. Min Act: -0.1700

Data Index: 403801 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3450. Min Act: -0.1700

Data Index: 685835 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3450. Min Act: -0.1700

Data Index: 760930 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3450. Min Act: -0.1700

Data Index: 1144687 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 3.5175. Min Range: -3.5175

Max Act: 3.3450. Min Act: -0.1700

Data Index: 344991 (C4 (Web Text))

Max Activating Token Index: 35