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

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

Neuron 351 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: 3.6876. Min Range: -3.6876

Max Act: 3.6876. Min Act: -0.1700

Data Index: 1188567 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.2319. Min Act: -0.1700

Data Index: 771612 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.2145. Min Act: -0.1700

Data Index: 994778 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.2027. Min Act: -0.1700

Data Index: 1033057 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1819. Min Act: -0.1700

Data Index: 800827 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1591. Min Act: -0.1700

Data Index: 783110 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1712. Min Act: -0.1700

Data Index: 1088323 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1272. Min Act: -0.1700

Data Index: 159634 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1273. Min Act: -0.1700

Data Index: 954 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1109. Min Act: -0.1700

Data Index: 763704 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1150. Min Act: -0.1700

Data Index: 739519 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1106. Min Act: -0.1699

Data Index: 594650 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1032. Min Act: -0.1700

Data Index: 228058 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1141. Min Act: -0.1700

Data Index: 695993 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1042. Min Act: -0.1699

Data Index: 643221 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.1002. Min Act: -0.1700

Data Index: 289093 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.0972. Min Act: -0.1700

Data Index: 125208 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.0870. Min Act: -0.1699

Data Index: 210146 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.0871. Min Act: -0.1700

Data Index: 693125 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.0874. Min Act: -0.1643

Data Index: 803583 (C4 (Web Text))

Max Activating Token Index: 666