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

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

Neuron 1145 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: 5.5795. Min Range: -5.5795

Max Act: 5.5795. Min Act: -0.1700

Data Index: 494782 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.3295. Min Act: -0.1700

Data Index: 1156340 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.2983. Min Act: -0.1700

Data Index: 754794 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.2045. Min Act: -0.1700

Data Index: 179402 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.2045. Min Act: -0.1700

Data Index: 102658 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.1420. Min Act: -0.1700

Data Index: 352740 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.1108. Min Act: -0.1700

Data Index: 458048 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.0483. Min Act: -0.1700

Data Index: 750880 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.0795. Min Act: -0.1700

Data Index: 1134055 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.0795. Min Act: -0.1700

Data Index: 1224992 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.0483. Min Act: -0.1700

Data Index: 924062 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 5.5795. Min Range: -5.5795

Max Act: 4.9858. Min Act: -0.1700

Data Index: 613696 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.0483. Min Act: -0.1700

Data Index: 660755 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 5.5795. Min Range: -5.5795

Max Act: 5.0170. Min Act: -0.1700

Data Index: 1094534 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 5.5795. Min Range: -5.5795

Max Act: 4.9858. Min Act: -0.1700

Data Index: 740091 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 5.5795. Min Range: -5.5795

Max Act: 4.9233. Min Act: -0.1700

Data Index: 3832 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 5.5795. Min Range: -5.5795

Max Act: 4.9233. Min Act: -0.1700

Data Index: 198719 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 5.5795. Min Range: -5.5795

Max Act: 4.9545. Min Act: -0.1700

Data Index: 1072383 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 5.5795. Min Range: -5.5795

Max Act: 4.9545. Min Act: -0.1700

Data Index: 872400 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 5.5795. Min Range: -5.5795

Max Act: 4.9545. Min Act: -0.1700

Data Index: 551044 (C4 (Web Text))

Max Activating Token Index: 502