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

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

Neuron 1645 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: 3.2263. Min Range: -3.2263

Max Act: 3.1948. Min Act: -0.1700

Data Index: 1407734 (Python Code)

Max Activating Token Index: 808

Text #1

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.2106. Min Act: -0.1700

Data Index: 1409361 (Python Code)

Max Activating Token Index: 627

Text #2

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.2263. Min Act: -0.1700

Data Index: 1639283 (Python Code)

Max Activating Token Index: 1010

Text #3

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1161. Min Act: -0.1700

Data Index: 1647271 (Python Code)

Max Activating Token Index: 537

Text #4

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.0056. Min Act: -0.1700

Data Index: 1605300 (Python Code)

Max Activating Token Index: 473

Text #5

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.0530. Min Act: -0.1700

Data Index: 1585370 (Python Code)

Max Activating Token Index: 1022

Text #6

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.0530. Min Act: -0.1700

Data Index: 1540874 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.0214. Min Act: -0.1700

Data Index: 1372320 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 3.2263. Min Range: -3.2263

Max Act: 2.9898. Min Act: -0.1700

Data Index: 1570813 (Python Code)

Max Activating Token Index: 158

Text #9

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.0056. Min Act: -0.1700

Data Index: 1580455 (Python Code)

Max Activating Token Index: 761

Text #10

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.0214. Min Act: -0.1700

Data Index: 1560048 (Python Code)

Max Activating Token Index: 443

Text #11

Max Range: 3.2263. Min Range: -3.2263

Max Act: 2.9740. Min Act: -0.1700

Data Index: 855173 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 3.2263. Min Range: -3.2263

Max Act: 2.9265. Min Act: -0.1700

Data Index: 1438714 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 3.2263. Min Range: -3.2263

Max Act: 2.9582. Min Act: -0.1700

Data Index: 1547944 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 3.2263. Min Range: -3.2263

Max Act: 2.9265. Min Act: -0.1700

Data Index: 1566676 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 3.2263. Min Range: -3.2263

Max Act: 2.9423. Min Act: -0.1700

Data Index: 1587089 (Python Code)

Max Activating Token Index: 936

Text #16

Max Range: 3.2263. Min Range: -3.2263

Max Act: 2.9423. Min Act: -0.1700

Data Index: 1424226 (Python Code)

Max Activating Token Index: 940

Text #17

Max Range: 3.2263. Min Range: -3.2263

Max Act: 2.9265. Min Act: -0.1700

Data Index: 1563223 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 3.2263. Min Range: -3.2263

Max Act: 2.9106. Min Act: -0.1700

Data Index: 1488479 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 3.2263. Min Range: -3.2263

Max Act: 2.9106. Min Act: -0.1700

Data Index: 1396961 (Python Code)

Max Activating Token Index: 30