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

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

Neuron 614 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: 3.2675. Min Range: -3.2675

Max Act: 3.2675. Min Act: -0.1700

Data Index: 196489 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.2518. Min Act: -0.1700

Data Index: 75019 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.2518. Min Act: -0.1700

Data Index: 1491064 (Python Code)

Max Activating Token Index: 70

Text #3

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.2204. Min Act: -0.1700

Data Index: 611922 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.2046. Min Act: -0.1700

Data Index: 4538 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.2046. Min Act: -0.1700

Data Index: 1259149 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1732. Min Act: -0.1700

Data Index: 1534998 (Python Code)

Max Activating Token Index: 669

Text #7

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1574. Min Act: -0.1700

Data Index: 1476566 (Python Code)

Max Activating Token Index: 102

Text #8

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1417. Min Act: -0.1700

Data Index: 235491 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1574. Min Act: -0.1700

Data Index: 957171 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1417. Min Act: -0.1700

Data Index: 66970 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1417. Min Act: -0.1700

Data Index: 579328 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1259. Min Act: -0.1700

Data Index: 820294 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1101. Min Act: -0.1700

Data Index: 432088 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1101. Min Act: -0.1700

Data Index: 193841 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1101. Min Act: -0.1700

Data Index: 1502169 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1101. Min Act: -0.1700

Data Index: 927174 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1101. Min Act: -0.1700

Data Index: 610727 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.0944. Min Act: -0.1700

Data Index: 631540 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 3.2675. Min Range: -3.2675

Max Act: 3.1101. Min Act: -0.1700

Data Index: 835587 (C4 (Web Text))

Max Activating Token Index: 733