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

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

Neuron 1883 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3347. Min Range: -5.3347

Max Act: 5.3347. Min Act: -0.1700

Data Index: 320727 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 5.3347. Min Range: -5.3347

Max Act: 5.0222. Min Act: -0.1700

Data Index: 129684 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.9284. Min Act: -0.1700

Data Index: 837493 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.7722. Min Act: -0.1700

Data Index: 1024537 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.7722. Min Act: -0.1700

Data Index: 1215386 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.7097. Min Act: -0.1700

Data Index: 906510 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.6784. Min Act: -0.1700

Data Index: 1220157 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.6784. Min Act: -0.1700

Data Index: 1203640 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.5847. Min Act: -0.1700

Data Index: 102036 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.6159. Min Act: -0.1700

Data Index: 56325 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.6159. Min Act: -0.1700

Data Index: 244198 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.5847. Min Act: -0.1700

Data Index: 285357 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.4909. Min Act: -0.1700

Data Index: 464729 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.5847. Min Act: -0.1700

Data Index: 290756 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.5222. Min Act: -0.1700

Data Index: 549248 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.4909. Min Act: -0.1700

Data Index: 1163768 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.5222. Min Act: -0.1700

Data Index: 272570 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.4597. Min Act: -0.1700

Data Index: 497198 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.4597. Min Act: -0.1700

Data Index: 1348421 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 5.3347. Min Range: -5.3347

Max Act: 4.4909. Min Act: -0.1700

Data Index: 541076 (C4 (Web Text))

Max Activating Token Index: 596