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

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

Neuron 1073 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: 4.2176. Min Range: -4.2176

Max Act: 4.2176. Min Act: -0.1700

Data Index: 264939 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.1318. Min Act: -0.1700

Data Index: 875686 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.1339. Min Act: -0.1700

Data Index: 348892 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0722. Min Act: -0.1700

Data Index: 704712 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.1016. Min Act: -0.1700

Data Index: 865869 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0833. Min Act: -0.1700

Data Index: 1159280 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0595. Min Act: -0.1700

Data Index: 324118 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0266. Min Act: -0.1700

Data Index: 894388 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0252. Min Act: -0.1700

Data Index: 1039777 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0588. Min Act: -0.1700

Data Index: 307774 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0443. Min Act: -0.1700

Data Index: 1089948 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0749. Min Act: -0.1700

Data Index: 936951 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0515. Min Act: -0.1700

Data Index: 278170 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0160. Min Act: -0.1700

Data Index: 647731 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0118. Min Act: -0.1700

Data Index: 774287 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0081. Min Act: -0.1700

Data Index: 1395347 (Python Code)

Max Activating Token Index: 379

Text #16

Max Range: 4.2176. Min Range: -4.2176

Max Act: 3.9669. Min Act: -0.1700

Data Index: 332919 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0021. Min Act: -0.1700

Data Index: 1083122 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 4.2176. Min Range: -4.2176

Max Act: 3.9649. Min Act: -0.1700

Data Index: 971965 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 4.2176. Min Range: -4.2176

Max Act: 4.0089. Min Act: -0.1700

Data Index: 1083286 (C4 (Web Text))

Max Activating Token Index: 166