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

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

Neuron 993 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: 3.5858. Min Range: -3.5858

Max Act: 3.5858. Min Act: -0.1700

Data Index: 187177 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3663. Min Act: -0.1700

Data Index: 293028 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3506. Min Act: -0.1700

Data Index: 899117 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2721. Min Act: -0.1700

Data Index: 347642 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3349. Min Act: -0.1700

Data Index: 1420276 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3192. Min Act: -0.1700

Data Index: 708534 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3035. Min Act: -0.1700

Data Index: 1074956 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3035. Min Act: -0.1700

Data Index: 1054431 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2878. Min Act: -0.1700

Data Index: 1098715 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3035. Min Act: -0.1700

Data Index: 265570 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2878. Min Act: -0.1700

Data Index: 67795 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.3035. Min Act: -0.1700

Data Index: 658999 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2878. Min Act: -0.1700

Data Index: 756198 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2407. Min Act: -0.1700

Data Index: 322511 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2564. Min Act: -0.1700

Data Index: 492200 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2564. Min Act: -0.1700

Data Index: 175724 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2721. Min Act: -0.1700

Data Index: 809881 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2407. Min Act: -0.1700

Data Index: 699539 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2878. Min Act: -0.1700

Data Index: 933060 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 3.5858. Min Range: -3.5858

Max Act: 3.2407. Min Act: -0.1700

Data Index: 455426 (C4 (Web Text))

Max Activating Token Index: 95