Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1796 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.5929. Min Act: -0.1700

Data Index: 1591783 (Python Code)

Max Activating Token Index: 403

Text #1

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.4679. Min Act: -0.1700

Data Index: 1620479 (Python Code)

Max Activating Token Index: 940

Text #2

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.4679. Min Act: -0.1700

Data Index: 1566170 (Python Code)

Max Activating Token Index: 871

Text #3

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.3742. Min Act: -0.1700

Data Index: 1528994 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.3117. Min Act: -0.1700

Data Index: 1603178 (Python Code)

Max Activating Token Index: 353

Text #5

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.3117. Min Act: -0.1700

Data Index: 1397584 (Python Code)

Max Activating Token Index: 753

Text #6

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.3117. Min Act: -0.1700

Data Index: 1518413 (Python Code)

Max Activating Token Index: 791

Text #7

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.3429. Min Act: -0.1699

Data Index: 1600399 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.2492. Min Act: -0.1700

Data Index: 1370536 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.3117. Min Act: -0.1700

Data Index: 1370281 (Python Code)

Max Activating Token Index: 475

Text #10

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.2804. Min Act: -0.1697

Data Index: 1617320 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.2492. Min Act: -0.1700

Data Index: 1563398 (Python Code)

Max Activating Token Index: 247

Text #12

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.2179. Min Act: -0.1700

Data Index: 1452098 (Python Code)

Max Activating Token Index: 565

Text #13

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.2492. Min Act: -0.1700

Data Index: 1379959 (Python Code)

Max Activating Token Index: 1020

Text #14

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.2179. Min Act: -0.1700

Data Index: 1583892 (Python Code)

Max Activating Token Index: 418

Text #15

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.1867. Min Act: -0.1700

Data Index: 1655840 (Python Code)

Max Activating Token Index: 969

Text #16

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.1867. Min Act: -0.1700

Data Index: 1493016 (Python Code)

Max Activating Token Index: 348

Text #17

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.1867. Min Act: -0.1700

Data Index: 1504873 (Python Code)

Max Activating Token Index: 559

Text #18

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.2179. Min Act: -0.1700

Data Index: 1411022 (Python Code)

Max Activating Token Index: 412

Text #19

Max Range: 5.5929. Min Range: -5.5929

Max Act: 5.1867. Min Act: -0.1700

Data Index: 1454948 (Python Code)

Max Activating Token Index: 529