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

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

Neuron 1085 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.3937. Min Act: -0.1700

Data Index: 298636 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.3152. Min Act: -0.1700

Data Index: 1291265 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.2209. Min Act: -0.1700

Data Index: 751268 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1895. Min Act: -0.1700

Data Index: 502136 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1737. Min Act: -0.1700

Data Index: 208745 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.2052. Min Act: -0.1700

Data Index: 115449 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1580. Min Act: -0.1700

Data Index: 20483 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1580. Min Act: -0.1700

Data Index: 88240 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1422. Min Act: -0.1700

Data Index: 414934 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1580. Min Act: -0.1700

Data Index: 1114941 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.0792. Min Act: -0.1700

Data Index: 339536 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1422. Min Act: -0.1700

Data Index: 898684 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1107. Min Act: -0.1700

Data Index: 913699 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.0950. Min Act: -0.1700

Data Index: 323691 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.0792. Min Act: -0.1700

Data Index: 259628 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.0634. Min Act: -0.1700

Data Index: 600336 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.0792. Min Act: -0.1700

Data Index: 365153 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.0634. Min Act: -0.1699

Data Index: 105023 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.0792. Min Act: -0.1700

Data Index: 1152557 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.0476. Min Act: -0.1700

Data Index: 738356 (C4 (Web Text))

Max Activating Token Index: 479