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

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

Neuron 1354 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.1331. Min Act: -0.1700

Data Index: 512804 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.1173. Min Act: -0.1700

Data Index: 377905 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.1331. Min Act: -0.1700

Data Index: 840915 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.1173. Min Act: -0.1700

Data Index: 1279847 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.1173. Min Act: -0.1700

Data Index: 944285 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.1015. Min Act: -0.1700

Data Index: 1111011 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.1015. Min Act: -0.1700

Data Index: 1117094 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.0858. Min Act: -0.1700

Data Index: 1337951 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.1015. Min Act: -0.1700

Data Index: 1356737 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.1015. Min Act: -0.1700

Data Index: 615637 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.1015. Min Act: -0.1700

Data Index: 238359 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.0700. Min Act: -0.1700

Data Index: 1051941 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.0700. Min Act: -0.1700

Data Index: 370044 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.0700. Min Act: -0.1700

Data Index: 230967 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.0858. Min Act: -0.1700

Data Index: 395093 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.1015. Min Act: -0.1700

Data Index: 830527 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.0858. Min Act: -0.1700

Data Index: 95359 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.0700. Min Act: -0.1700

Data Index: 444908 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.0858. Min Act: -0.1700

Data Index: 298154 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 3.1331. Min Range: -3.1331

Max Act: 3.0700. Min Act: -0.1700

Data Index: 1020547 (C4 (Web Text))

Max Activating Token Index: 823