Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 493 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.2081. Min Act: -0.1700

Data Index: 112906 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.2000. Min Act: -0.1700

Data Index: 1185497 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.2000. Min Act: -0.1700

Data Index: 1202621 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.1780. Min Act: -0.1700

Data Index: 933154 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.1835. Min Act: -0.1700

Data Index: 794089 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.1701. Min Act: -0.1700

Data Index: 342742 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.1574. Min Act: -0.1700

Data Index: 174858 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.1436. Min Act: -0.1700

Data Index: 864495 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.1214. Min Act: -0.1700

Data Index: 1601176 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.1089. Min Act: -0.1700

Data Index: 1187710 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.1059. Min Act: -0.1700

Data Index: 239035 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.0977. Min Act: -0.1700

Data Index: 282839 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.0924. Min Act: -0.1700

Data Index: 796531 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.0850. Min Act: -0.1700

Data Index: 1292425 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.1031. Min Act: -0.1700

Data Index: 713443 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.0972. Min Act: -0.1700

Data Index: 839426 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.0918. Min Act: -0.1700

Data Index: 1366393 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.0850. Min Act: -0.1700

Data Index: 1013976 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.0689. Min Act: -0.1700

Data Index: 1334929 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.0533. Min Act: -0.1700

Data Index: 308174 (C4 (Web Text))

Max Activating Token Index: 876