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

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

Neuron 1157 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: 5.0346. Min Range: -5.0346

Max Act: 5.0346. Min Act: -0.1700

Data Index: 1516225 (Python Code)

Max Activating Token Index: 766

Text #1

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.8471. Min Act: -0.1700

Data Index: 1525274 (Python Code)

Max Activating Token Index: 1001

Text #2

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.7689. Min Act: -0.1700

Data Index: 1544264 (Python Code)

Max Activating Token Index: 705

Text #3

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.7533. Min Act: -0.1700

Data Index: 1126380 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.4564. Min Act: -0.1700

Data Index: 1459045 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.5189. Min Act: -0.1700

Data Index: 1485906 (Python Code)

Max Activating Token Index: 716

Text #6

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.5346. Min Act: -0.1700

Data Index: 1636351 (Python Code)

Max Activating Token Index: 111

Text #7

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.5502. Min Act: -0.1700

Data Index: 1608670 (Python Code)

Max Activating Token Index: 883

Text #8

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.4877. Min Act: -0.1700

Data Index: 1624014 (Python Code)

Max Activating Token Index: 374

Text #9

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.4877. Min Act: -0.1700

Data Index: 1444652 (Python Code)

Max Activating Token Index: 852

Text #10

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.4877. Min Act: -0.1700

Data Index: 1455203 (Python Code)

Max Activating Token Index: 582

Text #11

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.4721. Min Act: -0.1700

Data Index: 1360274 (Python Code)

Max Activating Token Index: 640

Text #12

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.3939. Min Act: -0.1700

Data Index: 1363855 (Python Code)

Max Activating Token Index: 256

Text #13

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.4721. Min Act: -0.1700

Data Index: 1499215 (Python Code)

Max Activating Token Index: 480

Text #14

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.3783. Min Act: -0.1700

Data Index: 1374360 (Python Code)

Max Activating Token Index: 825

Text #15

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.4564. Min Act: -0.1700

Data Index: 1450079 (Python Code)

Max Activating Token Index: 791

Text #16

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.4408. Min Act: -0.1700

Data Index: 1503940 (Python Code)

Max Activating Token Index: 470

Text #17

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.3939. Min Act: -0.1700

Data Index: 1521653 (Python Code)

Max Activating Token Index: 663

Text #18

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.3939. Min Act: -0.1700

Data Index: 1550011 (Python Code)

Max Activating Token Index: 939

Text #19

Max Range: 5.0346. Min Range: -5.0346

Max Act: 4.4096. Min Act: -0.1700

Data Index: 1474032 (Python Code)

Max Activating Token Index: 843