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

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

Neuron 1824 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.8276. Min Act: -0.1700

Data Index: 782801 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.7963. Min Act: -0.1700

Data Index: 765286 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.7025. Min Act: -0.1700

Data Index: 306800 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6712. Min Act: -0.1700

Data Index: 813691 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6712. Min Act: -0.1700

Data Index: 252633 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6712. Min Act: -0.1700

Data Index: 854740 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1225887 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6399. Min Act: -0.1700

Data Index: 300031 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6086. Min Act: -0.1700

Data Index: 221754 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6086. Min Act: -0.1700

Data Index: 575812 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5773. Min Act: -0.1700

Data Index: 1091338 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6086. Min Act: -0.1700

Data Index: 830581 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6086. Min Act: -0.1700

Data Index: 600144 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1344561 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5773. Min Act: -0.1700

Data Index: 805018 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6086. Min Act: -0.1700

Data Index: 788498 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5459. Min Act: -0.1700

Data Index: 107833 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5773. Min Act: -0.1700

Data Index: 636195 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5773. Min Act: -0.1700

Data Index: 725998 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5773. Min Act: -0.1700

Data Index: 894206 (C4 (Web Text))

Max Activating Token Index: 268