Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 946 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.5913. Min Act: -0.1700

Data Index: 679779 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.4660. Min Act: -0.1700

Data Index: 1123362 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.4347. Min Act: -0.1700

Data Index: 898675 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.4033. Min Act: -0.1700

Data Index: 896940 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.4033. Min Act: -0.1700

Data Index: 1330364 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3876. Min Act: -0.1700

Data Index: 744293 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3876. Min Act: -0.1700

Data Index: 48182 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.4033. Min Act: -0.1700

Data Index: 90209 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.4190. Min Act: -0.1700

Data Index: 247956 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3876. Min Act: -0.1700

Data Index: 432249 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3562. Min Act: -0.1700

Data Index: 1161361 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3562. Min Act: -0.1700

Data Index: 318884 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3719. Min Act: -0.1700

Data Index: 1081119 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3562. Min Act: -0.1700

Data Index: 951891 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3405. Min Act: -0.1700

Data Index: 1080223 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3562. Min Act: -0.1700

Data Index: 1245117 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3405. Min Act: -0.1700

Data Index: 365185 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3562. Min Act: -0.1700

Data Index: 293841 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3562. Min Act: -0.1700

Data Index: 988540 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 3.5913. Min Range: -3.5913

Max Act: 3.3405. Min Act: -0.1700

Data Index: 759557 (C4 (Web Text))

Max Activating Token Index: 951