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

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

Neuron 1263 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: 3.4083. Min Range: -3.4083

Max Act: 3.4083. Min Act: -0.1700

Data Index: 433317 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.3142. Min Act: -0.1700

Data Index: 760589 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.3142. Min Act: -0.1700

Data Index: 685127 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.2828. Min Act: -0.1700

Data Index: 31090 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.2513. Min Act: -0.1700

Data Index: 68449 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.2828. Min Act: -0.1700

Data Index: 1047955 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.2199. Min Act: -0.1700

Data Index: 650316 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1570. Min Act: -0.1700

Data Index: 816199 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1412. Min Act: -0.1700

Data Index: 783489 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1884. Min Act: -0.1700

Data Index: 355066 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1884. Min Act: -0.1700

Data Index: 750736 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1884. Min Act: -0.1700

Data Index: 336230 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1884. Min Act: -0.1700

Data Index: 704501 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1412. Min Act: -0.1700

Data Index: 856842 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1570. Min Act: -0.1700

Data Index: 974292 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1255. Min Act: -0.1700

Data Index: 561892 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1097. Min Act: -0.1700

Data Index: 188966 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.0782. Min Act: -0.1700

Data Index: 625674 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1097. Min Act: -0.1700

Data Index: 27109 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 3.4083. Min Range: -3.4083

Max Act: 3.1097. Min Act: -0.1700

Data Index: 237820 (C4 (Web Text))

Max Activating Token Index: 212