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

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

Neuron 243 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: 3.3135. Min Range: -3.3135

Max Act: 3.2978. Min Act: -0.1700

Data Index: 1594466 (Python Code)

Max Activating Token Index: 423

Text #1

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.3135. Min Act: -0.1700

Data Index: 332867 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.2506. Min Act: -0.1700

Data Index: 1461501 (Python Code)

Max Activating Token Index: 916

Text #3

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.2349. Min Act: -0.1700

Data Index: 859917 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.2035. Min Act: -0.1700

Data Index: 1439170 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.2035. Min Act: -0.1700

Data Index: 199102 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.1720. Min Act: -0.1700

Data Index: 1362767 (Python Code)

Max Activating Token Index: 145

Text #7

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.1405. Min Act: -0.1700

Data Index: 1384630 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.1720. Min Act: -0.1700

Data Index: 185616 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.1562. Min Act: -0.1700

Data Index: 302004 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.1405. Min Act: -0.1700

Data Index: 1499965 (Python Code)

Max Activating Token Index: 364

Text #11

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.1247. Min Act: -0.1700

Data Index: 819461 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.1247. Min Act: -0.1700

Data Index: 1458476 (Python Code)

Max Activating Token Index: 548

Text #13

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.0774. Min Act: -0.1700

Data Index: 1526935 (Python Code)

Max Activating Token Index: 950

Text #14

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.1247. Min Act: -0.1700

Data Index: 250933 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.0932. Min Act: -0.1700

Data Index: 1477753 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.0932. Min Act: -0.1700

Data Index: 1455596 (Python Code)

Max Activating Token Index: 824

Text #17

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.1247. Min Act: -0.1700

Data Index: 1439081 (Python Code)

Max Activating Token Index: 262

Text #18

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.0774. Min Act: -0.1700

Data Index: 1511787 (Python Code)

Max Activating Token Index: 213

Text #19

Max Range: 3.3135. Min Range: -3.3135

Max Act: 3.0459. Min Act: -0.1700

Data Index: 1413453 (Python Code)

Max Activating Token Index: 601