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

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

Neuron 1892 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: 3.1596. Min Range: -3.1596

Max Act: 3.1596. Min Act: -0.1700

Data Index: 982779 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.1281. Min Act: -0.1700

Data Index: 1267215 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0966. Min Act: -0.1700

Data Index: 1136232 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0966. Min Act: -0.1700

Data Index: 885417 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.1123. Min Act: -0.1700

Data Index: 243188 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.1123. Min Act: -0.1700

Data Index: 576928 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0966. Min Act: -0.1700

Data Index: 1241747 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.1123. Min Act: -0.1700

Data Index: 1326556 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0808. Min Act: -0.1700

Data Index: 851091 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0966. Min Act: -0.1700

Data Index: 119701 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.1123. Min Act: -0.1699

Data Index: 590098 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0966. Min Act: -0.1700

Data Index: 1245284 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0966. Min Act: -0.1700

Data Index: 458329 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0966. Min Act: -0.1700

Data Index: 813552 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0808. Min Act: -0.1700

Data Index: 1224516 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0808. Min Act: -0.1700

Data Index: 546726 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0966. Min Act: -0.1700

Data Index: 280970 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0808. Min Act: -0.1700

Data Index: 312809 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0966. Min Act: -0.1700

Data Index: 639383 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.1596. Min Range: -3.1596

Max Act: 3.0808. Min Act: -0.1700

Data Index: 510366 (C4 (Web Text))

Max Activating Token Index: 582