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

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

Neuron 518 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.5148. Min Act: -0.1700

Data Index: 724602 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.4523. Min Act: -0.1700

Data Index: 552160 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.4211. Min Act: -0.1700

Data Index: 1313857 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.2961. Min Act: -0.1700

Data Index: 479078 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.4523. Min Act: -0.1700

Data Index: 1149207 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.4211. Min Act: -0.1700

Data Index: 1142607 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.3898. Min Act: -0.1700

Data Index: 1073579 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.3586. Min Act: -0.1700

Data Index: 639305 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.2961. Min Act: -0.1700

Data Index: 1153106 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.2648. Min Act: -0.1700

Data Index: 567382 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.3898. Min Act: -0.1700

Data Index: 791628 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.4211. Min Act: -0.1700

Data Index: 33271 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.2961. Min Act: -0.1700

Data Index: 1118189 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.3273. Min Act: -0.1700

Data Index: 227518 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.2648. Min Act: -0.1700

Data Index: 660127 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.3273. Min Act: -0.1700

Data Index: 1107023 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.3273. Min Act: -0.1700

Data Index: 418188 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.2961. Min Act: -0.1700

Data Index: 918036 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.2336. Min Act: -0.1700

Data Index: 285318 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 5.5148. Min Range: -5.5148

Max Act: 5.2648. Min Act: -0.1700

Data Index: 132814 (C4 (Web Text))

Max Activating Token Index: 86