Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1056 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.8072. Min Act: -0.1700

Data Index: 577820 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.6510. Min Act: -0.1700

Data Index: 856617 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.8072. Min Act: -0.1700

Data Index: 784331 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.5885. Min Act: -0.1700

Data Index: 661203 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.7135. Min Act: -0.1700

Data Index: 1313100 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.6822. Min Act: -0.1700

Data Index: 715248 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.7135. Min Act: -0.1700

Data Index: 660909 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.6510. Min Act: -0.1700

Data Index: 903183 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.7447. Min Act: -0.1700

Data Index: 636802 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.6822. Min Act: -0.1700

Data Index: 1129659 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.7447. Min Act: -0.1700

Data Index: 857434 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.6822. Min Act: -0.1700

Data Index: 1298532 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.7447. Min Act: -0.1700

Data Index: 1009002 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.5572. Min Act: -0.1700

Data Index: 637522 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.5572. Min Act: -0.1700

Data Index: 264434 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.6510. Min Act: -0.1700

Data Index: 518961 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.7135. Min Act: -0.1700

Data Index: 304003 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.4322. Min Act: -0.1700

Data Index: 500476 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.6822. Min Act: -0.1700

Data Index: 145465 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 5.8072. Min Range: -5.8072

Max Act: 5.5572. Min Act: -0.1700

Data Index: 310669 (C4 (Web Text))

Max Activating Token Index: 231