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

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

Neuron 1815 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.6922. Min Act: -0.1700

Data Index: 1023728 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.4730. Min Act: -0.1700

Data Index: 25399 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.4730. Min Act: -0.1700

Data Index: 950120 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.4417. Min Act: -0.1700

Data Index: 682470 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.3789. Min Act: -0.1700

Data Index: 627447 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.3789. Min Act: -0.1700

Data Index: 800217 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.2847. Min Act: -0.1700

Data Index: 658117 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.3789. Min Act: -0.1700

Data Index: 807151 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.2847. Min Act: -0.1700

Data Index: 104617 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.3161. Min Act: -0.1700

Data Index: 37477 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.3161. Min Act: -0.1700

Data Index: 216947 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.3161. Min Act: -0.1700

Data Index: 153116 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.2533. Min Act: -0.1700

Data Index: 28702 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.2533. Min Act: -0.1700

Data Index: 255562 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.2533. Min Act: -0.1700

Data Index: 926929 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.2847. Min Act: -0.1700

Data Index: 831402 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.2533. Min Act: -0.1700

Data Index: 1240896 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.2219. Min Act: -0.1700

Data Index: 3451 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.2533. Min Act: -0.1700

Data Index: 539328 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 3.6922. Min Range: -3.6922

Max Act: 3.2219. Min Act: -0.1700

Data Index: 77698 (C4 (Web Text))

Max Activating Token Index: 215