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

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

Neuron 944 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3910. Min Act: -0.1700

Data Index: 1457280 (Python Code)

Max Activating Token Index: 142

Text #1

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.4067. Min Act: -0.1700

Data Index: 1594492 (Python Code)

Max Activating Token Index: 724

Text #2

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3910. Min Act: -0.1700

Data Index: 1472781 (Python Code)

Max Activating Token Index: 979

Text #3

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3597. Min Act: -0.1700

Data Index: 754438 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3597. Min Act: -0.1700

Data Index: 1529106 (Python Code)

Max Activating Token Index: 76

Text #5

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3440. Min Act: -0.1700

Data Index: 588911 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3283. Min Act: -0.1700

Data Index: 1508594 (Python Code)

Max Activating Token Index: 524

Text #7

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3440. Min Act: -0.1700

Data Index: 861115 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3126. Min Act: -0.1700

Data Index: 45590 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3283. Min Act: -0.1700

Data Index: 1599764 (Python Code)

Max Activating Token Index: 903

Text #10

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3126. Min Act: -0.1700

Data Index: 1085876 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3126. Min Act: -0.1700

Data Index: 1258537 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3126. Min Act: -0.1700

Data Index: 686246 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3283. Min Act: -0.1700

Data Index: 532728 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2969. Min Act: -0.1700

Data Index: 1494616 (Python Code)

Max Activating Token Index: 507

Text #15

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2969. Min Act: -0.1700

Data Index: 788166 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3126. Min Act: -0.1700

Data Index: 654157 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2969. Min Act: -0.1700

Data Index: 1197822 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3126. Min Act: -0.1700

Data Index: 520966 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3126. Min Act: -0.1700

Data Index: 861507 (C4 (Web Text))

Max Activating Token Index: 262