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

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

Neuron 535 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: 3.3557. Min Range: -3.3557

Max Act: 3.3557. Min Act: -0.1700

Data Index: 842103 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.3086. Min Act: -0.1700

Data Index: 1317204 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.3243. Min Act: -0.1700

Data Index: 1402619 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2772. Min Act: -0.1700

Data Index: 129950 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2929. Min Act: -0.1700

Data Index: 791273 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2929. Min Act: -0.1700

Data Index: 329445 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2929. Min Act: -0.1700

Data Index: 943419 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2615. Min Act: -0.1700

Data Index: 796832 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2772. Min Act: -0.1700

Data Index: 957620 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2772. Min Act: -0.1700

Data Index: 1093277 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2615. Min Act: -0.1700

Data Index: 719542 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2143. Min Act: -0.1700

Data Index: 1637895 (Python Code)

Max Activating Token Index: 505

Text #12

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2458. Min Act: -0.1700

Data Index: 538109 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2615. Min Act: -0.1700

Data Index: 855273 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2458. Min Act: -0.1700

Data Index: 612119 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2143. Min Act: -0.1700

Data Index: 750683 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.1986. Min Act: -0.1700

Data Index: 1092149 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.2143. Min Act: -0.1700

Data Index: 220179 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.1986. Min Act: -0.1700

Data Index: 1631086 (Python Code)

Max Activating Token Index: 143

Text #19

Max Range: 3.3557. Min Range: -3.3557

Max Act: 3.1986. Min Act: -0.1700

Data Index: 231909 (C4 (Web Text))

Max Activating Token Index: 1014