Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1681 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0967. Min Range: -3.0967

Max Act: 3.0967. Min Act: -0.1700

Data Index: 1068922 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 3.0967. Min Range: -3.0967

Max Act: 3.0728. Min Act: -0.1700

Data Index: 1353050 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 3.0967. Min Range: -3.0967

Max Act: 3.0352. Min Act: -0.1700

Data Index: 123497 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 3.0967. Min Range: -3.0967

Max Act: 3.0134. Min Act: -0.1700

Data Index: 502891 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 3.0967. Min Range: -3.0967

Max Act: 3.0022. Min Act: -0.1700

Data Index: 1472868 (Python Code)

Max Activating Token Index: 669

Text #5

Max Range: 3.0967. Min Range: -3.0967

Max Act: 3.0195. Min Act: -0.1700

Data Index: 622174 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.9857. Min Act: -0.1700

Data Index: 1319247 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.9723. Min Act: -0.1700

Data Index: 930702 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.8963. Min Act: -0.1700

Data Index: 1002065 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.9299. Min Act: -0.1700

Data Index: 119613 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.9371. Min Act: -0.1700

Data Index: 996960 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.9353. Min Act: -0.1700

Data Index: 1106927 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.9014. Min Act: -0.1700

Data Index: 1600581 (Python Code)

Max Activating Token Index: 680

Text #13

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.8736. Min Act: -0.1700

Data Index: 509376 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.9033. Min Act: -0.1700

Data Index: 507343 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.9053. Min Act: -0.1700

Data Index: 195924 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.8882. Min Act: -0.1700

Data Index: 1136400 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.8977. Min Act: -0.1700

Data Index: 589039 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.8863. Min Act: -0.1700

Data Index: 624296 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 3.0967. Min Range: -3.0967

Max Act: 2.8646. Min Act: -0.1700

Data Index: 1640079 (Python Code)

Max Activating Token Index: 368