Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 707 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7712. Min Act: -0.1700

Data Index: 79478 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7556. Min Act: -0.1700

Data Index: 717364 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7556. Min Act: -0.1700

Data Index: 391893 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7399. Min Act: -0.1700

Data Index: 1145640 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7556. Min Act: -0.1700

Data Index: 822553 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7399. Min Act: -0.1700

Data Index: 203516 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7556. Min Act: -0.1700

Data Index: 267890 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7399. Min Act: -0.1700

Data Index: 644175 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7399. Min Act: -0.1700

Data Index: 1347563 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7399. Min Act: -0.1700

Data Index: 24754 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7243. Min Act: -0.1700

Data Index: 898361 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7243. Min Act: -0.1700

Data Index: 1344648 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7086. Min Act: -0.1700

Data Index: 1023245 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7243. Min Act: -0.1700

Data Index: 943827 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7243. Min Act: -0.1700

Data Index: 17476 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.6930. Min Act: -0.1700

Data Index: 293590 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7086. Min Act: -0.1700

Data Index: 465714 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7086. Min Act: -0.1700

Data Index: 652438 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.7086. Min Act: -0.1700

Data Index: 901632 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 3.7712. Min Range: -3.7712

Max Act: 3.6930. Min Act: -0.1700

Data Index: 104598 (C4 (Web Text))

Max Activating Token Index: 366