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

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

Neuron 1537 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: 3.8288. Min Range: -3.8288

Max Act: 3.7975. Min Act: -0.1700

Data Index: 1245999 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.8288. Min Act: -0.1700

Data Index: 1172740 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7975. Min Act: -0.1700

Data Index: 204849 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7975. Min Act: -0.1700

Data Index: 858364 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7350. Min Act: -0.1700

Data Index: 657484 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.6411. Min Act: -0.1700

Data Index: 984076 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.6411. Min Act: -0.1700

Data Index: 1051768 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5784. Min Act: -0.1700

Data Index: 2625 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5784. Min Act: -0.1700

Data Index: 679699 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5471. Min Act: -0.1700

Data Index: 320849 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.6098. Min Act: -0.1700

Data Index: 747118 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5471. Min Act: -0.1700

Data Index: 381588 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5784. Min Act: -0.1700

Data Index: 530808 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5158. Min Act: -0.1700

Data Index: 213769 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5471. Min Act: -0.1700

Data Index: 972875 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5471. Min Act: -0.1700

Data Index: 182426 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5471. Min Act: -0.1700

Data Index: 1479004 (Python Code)

Max Activating Token Index: 546

Text #17

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5158. Min Act: -0.1700

Data Index: 417270 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5158. Min Act: -0.1700

Data Index: 1071365 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.5158. Min Act: -0.1700

Data Index: 464892 (C4 (Web Text))

Max Activating Token Index: 790