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

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

Neuron 1388 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.3413. Min Act: -0.1700

Data Index: 1553875 (Python Code)

Max Activating Token Index: 504

Text #1

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.1842. Min Act: -0.1700

Data Index: 1066626 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.2156. Min Act: -0.1700

Data Index: 1051063 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.1527. Min Act: -0.1700

Data Index: 300823 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.1842. Min Act: -0.1700

Data Index: 836872 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.1212. Min Act: -0.1700

Data Index: 80303 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.1527. Min Act: -0.1700

Data Index: 809552 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.1212. Min Act: -0.1700

Data Index: 389420 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.0897. Min Act: -0.1700

Data Index: 214238 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.0581. Min Act: -0.1700

Data Index: 545066 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.0581. Min Act: -0.1700

Data Index: 1389312 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.0581. Min Act: -0.1700

Data Index: 831193 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.0265. Min Act: -0.1699

Data Index: 961135 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.0265. Min Act: -0.1700

Data Index: 1177056 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 3.3413. Min Range: -3.3413

Max Act: 2.9949. Min Act: -0.1700

Data Index: 173194 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.0581. Min Act: -0.1700

Data Index: 370352 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.0265. Min Act: -0.1700

Data Index: 551643 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 3.3413. Min Range: -3.3413

Max Act: 3.0265. Min Act: -0.1700

Data Index: 33798 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 3.3413. Min Range: -3.3413

Max Act: 2.9949. Min Act: -0.1700

Data Index: 127217 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 3.3413. Min Range: -3.3413

Max Act: 2.9949. Min Act: -0.1700

Data Index: 1304442 (C4 (Web Text))

Max Activating Token Index: 1007