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

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

Neuron 1255 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: 3.7191. Min Range: -3.7191

Max Act: 3.7191. Min Act: -0.1700

Data Index: 1295488 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.4842. Min Act: -0.1700

Data Index: 447742 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.4842. Min Act: -0.1700

Data Index: 306285 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.4215. Min Act: -0.1700

Data Index: 701197 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.4529. Min Act: -0.1700

Data Index: 365537 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.4529. Min Act: -0.1700

Data Index: 367425 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.4215. Min Act: -0.1700

Data Index: 1219191 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.4686. Min Act: -0.1700

Data Index: 589515 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.3588. Min Act: -0.1700

Data Index: 1228667 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.4372. Min Act: -0.1700

Data Index: 392136 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.4059. Min Act: -0.1700

Data Index: 692918 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.3902. Min Act: -0.1700

Data Index: 116200 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.3902. Min Act: -0.1700

Data Index: 78140 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.3745. Min Act: -0.1700

Data Index: 591801 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.3902. Min Act: -0.1700

Data Index: 759937 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.3274. Min Act: -0.1700

Data Index: 976269 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.3745. Min Act: -0.1700

Data Index: 864516 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.3588. Min Act: -0.1700

Data Index: 1217214 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.3745. Min Act: -0.1700

Data Index: 20075 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 3.7191. Min Range: -3.7191

Max Act: 3.3588. Min Act: -0.1700

Data Index: 1067804 (C4 (Web Text))

Max Activating Token Index: 133