Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 285 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.5243. Min Act: -0.1700

Data Index: 1208065 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.2743. Min Act: -0.1700

Data Index: 1133052 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.2431. Min Act: -0.1700

Data Index: 348153 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.2743. Min Act: -0.1700

Data Index: 205208 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.2431. Min Act: -0.1700

Data Index: 497325 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.1806. Min Act: -0.1700

Data Index: 1062599 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.2118. Min Act: -0.1700

Data Index: 660909 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.0868. Min Act: -0.1700

Data Index: 115972 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.0556. Min Act: -0.1700

Data Index: 322551 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.1806. Min Act: -0.1700

Data Index: 1129659 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.1181. Min Act: -0.1700

Data Index: 1148993 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.1181. Min Act: -0.1700

Data Index: 199479 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.0868. Min Act: -0.1700

Data Index: 809054 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.1493. Min Act: -0.1700

Data Index: 356539 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.0868. Min Act: -0.1700

Data Index: 873984 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.0556. Min Act: -0.1700

Data Index: 903183 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.0868. Min Act: -0.1700

Data Index: 351969 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.0868. Min Act: -0.1700

Data Index: 1055002 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.0868. Min Act: -0.1700

Data Index: 1009002 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.0868. Min Act: -0.1700

Data Index: 483064 (C4 (Web Text))

Max Activating Token Index: 910