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

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

Neuron 852 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: 3.1891. Min Range: -3.1891

Max Act: 3.1891. Min Act: -0.1700

Data Index: 23572 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.1733. Min Act: -0.1700

Data Index: 1147482 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.1261. Min Act: -0.1700

Data Index: 108336 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0630. Min Act: -0.1700

Data Index: 206355 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0946. Min Act: -0.1700

Data Index: 260892 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0788. Min Act: -0.1700

Data Index: 1175103 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0788. Min Act: -0.1700

Data Index: 1054751 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0472. Min Act: -0.1700

Data Index: 41784 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0472. Min Act: -0.1700

Data Index: 482610 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0788. Min Act: -0.1700

Data Index: 667817 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0314. Min Act: -0.1700

Data Index: 384042 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0472. Min Act: -0.1700

Data Index: 1324659 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0314. Min Act: -0.1700

Data Index: 282445 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0156. Min Act: -0.1700

Data Index: 103961 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0314. Min Act: -0.1700

Data Index: 995857 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 3.1891. Min Range: -3.1891

Max Act: 2.9998. Min Act: -0.1700

Data Index: 47794 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0156. Min Act: -0.1700

Data Index: 297671 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0314. Min Act: -0.1700

Data Index: 1003566 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0156. Min Act: -0.1700

Data Index: 594043 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 3.1891. Min Range: -3.1891

Max Act: 2.9998. Min Act: -0.1700

Data Index: 1329143 (C4 (Web Text))

Max Activating Token Index: 944