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

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

Neuron 774 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.0533. Min Range: -7.0533

Max Act: 7.0533. Min Act: -0.1700

Data Index: 1593492 (Python Code)

Max Activating Token Index: 192

Text #1

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.7095. Min Act: -0.1700

Data Index: 1455298 (Python Code)

Max Activating Token Index: 44

Text #2

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.6783. Min Act: -0.1700

Data Index: 1394098 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.5845. Min Act: -0.1700

Data Index: 1627656 (Python Code)

Max Activating Token Index: 344

Text #4

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.4595. Min Act: -0.1700

Data Index: 1363671 (Python Code)

Max Activating Token Index: 101

Text #5

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.4595. Min Act: -0.1700

Data Index: 1622298 (Python Code)

Max Activating Token Index: 198

Text #6

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.4595. Min Act: -0.1700

Data Index: 1471757 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.3658. Min Act: -0.1700

Data Index: 1542980 (Python Code)

Max Activating Token Index: 537

Text #8

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.4283. Min Act: -0.1700

Data Index: 1636904 (Python Code)

Max Activating Token Index: 221

Text #9

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.3345. Min Act: -0.1700

Data Index: 1384927 (Python Code)

Max Activating Token Index: 823

Text #10

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.3033. Min Act: -0.1700

Data Index: 1542598 (Python Code)

Max Activating Token Index: 154

Text #11

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.3033. Min Act: -0.1699

Data Index: 1515294 (Python Code)

Max Activating Token Index: 639

Text #12

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.3345. Min Act: -0.1700

Data Index: 1587993 (Python Code)

Max Activating Token Index: 685

Text #13

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.3345. Min Act: -0.1700

Data Index: 1509316 (Python Code)

Max Activating Token Index: 748

Text #14

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.3033. Min Act: -0.1700

Data Index: 1594521 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.2720. Min Act: -0.1700

Data Index: 1384183 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.2720. Min Act: -0.1700

Data Index: 1392456 (Python Code)

Max Activating Token Index: 124

Text #17

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.3033. Min Act: -0.1700

Data Index: 1451495 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.1783. Min Act: -0.1700

Data Index: 1360030 (Python Code)

Max Activating Token Index: 912

Text #19

Max Range: 7.0533. Min Range: -7.0533

Max Act: 6.2408. Min Act: -0.1700

Data Index: 1447544 (Python Code)

Max Activating Token Index: 14