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

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

Neuron 150 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: 3.4540. Min Range: -3.4540

Max Act: 3.4540. Min Act: -0.1700

Data Index: 180511 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.3913. Min Act: -0.1700

Data Index: 532283 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.3756. Min Act: -0.1700

Data Index: 659143 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.3442. Min Act: -0.1700

Data Index: 964771 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.3442. Min Act: -0.1700

Data Index: 486818 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.3285. Min Act: -0.1700

Data Index: 275898 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.3285. Min Act: -0.1700

Data Index: 636275 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2971. Min Act: -0.1700

Data Index: 1190687 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2814. Min Act: -0.1700

Data Index: 701116 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2814. Min Act: -0.1700

Data Index: 1290256 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.3285. Min Act: -0.1700

Data Index: 438790 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2971. Min Act: -0.1700

Data Index: 4528 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2814. Min Act: -0.1700

Data Index: 925938 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2657. Min Act: -0.1700

Data Index: 814209 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2657. Min Act: -0.1700

Data Index: 75873 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2342. Min Act: -0.1700

Data Index: 494093 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2657. Min Act: -0.1700

Data Index: 649713 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2657. Min Act: -0.1700

Data Index: 511972 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2500. Min Act: -0.1700

Data Index: 780700 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2500. Min Act: -0.1700

Data Index: 549696 (C4 (Web Text))

Max Activating Token Index: 33