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

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

Neuron 384 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: 3.7661. Min Range: -3.7661

Max Act: 3.7661. Min Act: -0.1700

Data Index: 174518 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.6566. Min Act: -0.1700

Data Index: 1284485 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.6253. Min Act: -0.1700

Data Index: 1055503 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.6409. Min Act: -0.1700

Data Index: 118662 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.6253. Min Act: -0.1700

Data Index: 1337776 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.6096. Min Act: -0.1700

Data Index: 677530 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5626. Min Act: -0.1700

Data Index: 1103911 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5470. Min Act: -0.1700

Data Index: 680759 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5783. Min Act: -0.1700

Data Index: 1093255 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5470. Min Act: -0.1700

Data Index: 654206 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5626. Min Act: -0.1700

Data Index: 656944 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5470. Min Act: -0.1700

Data Index: 1376543 (Python Code)

Max Activating Token Index: 995

Text #12

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5470. Min Act: -0.1700

Data Index: 586677 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5470. Min Act: -0.1700

Data Index: 743166 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5470. Min Act: -0.1700

Data Index: 977624 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5470. Min Act: -0.1700

Data Index: 290701 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5313. Min Act: -0.1700

Data Index: 872481 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5313. Min Act: -0.1700

Data Index: 1081992 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5313. Min Act: -0.1700

Data Index: 880461 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 3.7661. Min Range: -3.7661

Max Act: 3.5313. Min Act: -0.1700

Data Index: 557177 (C4 (Web Text))

Max Activating Token Index: 719