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

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

Neuron 1899 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: 5.2370. Min Range: -5.2370

Max Act: 5.2370. Min Act: -0.1700

Data Index: 274858 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 5.2370. Min Range: -5.2370

Max Act: 5.1120. Min Act: -0.1700

Data Index: 1211804 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 5.2370. Min Range: -5.2370

Max Act: 5.0808. Min Act: -0.1700

Data Index: 145169 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 5.2370. Min Range: -5.2370

Max Act: 5.0495. Min Act: -0.1700

Data Index: 592578 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 5.2370. Min Range: -5.2370

Max Act: 5.0495. Min Act: -0.1700

Data Index: 1317004 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 5.2370. Min Range: -5.2370

Max Act: 5.0495. Min Act: -0.1700

Data Index: 475339 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.9245. Min Act: -0.1700

Data Index: 890783 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.9870. Min Act: -0.1700

Data Index: 299141 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.9558. Min Act: -0.1700

Data Index: 202805 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.9245. Min Act: -0.1700

Data Index: 16522 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.9245. Min Act: -0.1700

Data Index: 311103 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.9245. Min Act: -0.1700

Data Index: 3333 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.8933. Min Act: -0.1700

Data Index: 1099754 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.8933. Min Act: -0.1700

Data Index: 243762 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.8620. Min Act: -0.1700

Data Index: 129039 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.8620. Min Act: -0.1700

Data Index: 526220 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.8308. Min Act: -0.1700

Data Index: 795391 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.7683. Min Act: -0.1700

Data Index: 268439 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.8308. Min Act: -0.1700

Data Index: 284390 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 5.2370. Min Range: -5.2370

Max Act: 4.8308. Min Act: -0.1700

Data Index: 1292948 (C4 (Web Text))

Max Activating Token Index: 944