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

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

Neuron 982 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: 3.5524. Min Range: -3.5524

Max Act: 3.5524. Min Act: -0.1700

Data Index: 268728 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.3486. Min Act: -0.1700

Data Index: 465371 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.2858. Min Act: -0.1700

Data Index: 629061 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.2386. Min Act: -0.1700

Data Index: 831131 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.2543. Min Act: -0.1700

Data Index: 1306365 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.2858. Min Act: -0.1700

Data Index: 1101134 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.2386. Min Act: -0.1700

Data Index: 1164331 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.2700. Min Act: -0.1700

Data Index: 985239 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.2229. Min Act: -0.1700

Data Index: 767737 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.2386. Min Act: -0.1700

Data Index: 1332812 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.2229. Min Act: -0.1700

Data Index: 1196972 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.1914. Min Act: -0.1700

Data Index: 657058 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.2229. Min Act: -0.1700

Data Index: 1077185 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.1757. Min Act: -0.1700

Data Index: 1303362 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.1599. Min Act: -0.1700

Data Index: 654901 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.1599. Min Act: -0.1700

Data Index: 1332176 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.1599. Min Act: -0.1700

Data Index: 518936 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.1914. Min Act: -0.1700

Data Index: 397111 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.1284. Min Act: -0.1700

Data Index: 1088017 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.1442. Min Act: -0.1700

Data Index: 657036 (C4 (Web Text))

Max Activating Token Index: 853