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

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

Neuron 1582 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1988. Min Act: -0.1699

Data Index: 1507354 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1831. Min Act: -0.1700

Data Index: 1655264 (Python Code)

Max Activating Token Index: 161

Text #2

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1516. Min Act: -0.1700

Data Index: 1449761 (Python Code)

Max Activating Token Index: 491

Text #3

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1673. Min Act: -0.1700

Data Index: 1522910 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1358. Min Act: -0.1700

Data Index: 1405375 (Python Code)

Max Activating Token Index: 150

Text #5

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1358. Min Act: -0.1700

Data Index: 1499475 (Python Code)

Max Activating Token Index: 281

Text #6

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1043. Min Act: -0.1700

Data Index: 510475 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1201. Min Act: -0.1700

Data Index: 1391556 (Python Code)

Max Activating Token Index: 602

Text #8

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1201. Min Act: -0.1700

Data Index: 1599298 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1201. Min Act: -0.1700

Data Index: 1558381 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1201. Min Act: -0.1700

Data Index: 1494602 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.1043. Min Act: -0.1700

Data Index: 1531739 (Python Code)

Max Activating Token Index: 380

Text #12

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.0885. Min Act: -0.1700

Data Index: 1365160 (Python Code)

Max Activating Token Index: 269

Text #13

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.0885. Min Act: -0.1700

Data Index: 1398826 (Python Code)

Max Activating Token Index: 250

Text #14

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.0885. Min Act: -0.1700

Data Index: 1511083 (Python Code)

Max Activating Token Index: 472

Text #15

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.0728. Min Act: -0.1700

Data Index: 1381777 (Python Code)

Max Activating Token Index: 923

Text #16

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.0728. Min Act: -0.1700

Data Index: 1363202 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.0728. Min Act: -0.1700

Data Index: 1408580 (Python Code)

Max Activating Token Index: 752

Text #18

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.0570. Min Act: -0.1700

Data Index: 1602290 (Python Code)

Max Activating Token Index: 874

Text #19

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.0570. Min Act: -0.1700

Data Index: 1415719 (Python Code)

Max Activating Token Index: 902