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

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

Neuron 95 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.7006. Min Act: -0.1700

Data Index: 1496089 (Python Code)

Max Activating Token Index: 158

Text #1

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.7319. Min Act: -0.1700

Data Index: 1544443 (Python Code)

Max Activating Token Index: 76

Text #2

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.7006. Min Act: -0.1700

Data Index: 1546241 (Python Code)

Max Activating Token Index: 289

Text #3

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.7006. Min Act: -0.1700

Data Index: 1594474 (Python Code)

Max Activating Token Index: 117

Text #4

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.7319. Min Act: -0.1700

Data Index: 1569982 (Python Code)

Max Activating Token Index: 33

Text #5

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.7006. Min Act: -0.1700

Data Index: 1379077 (Python Code)

Max Activating Token Index: 531

Text #6

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.6694. Min Act: -0.1700

Data Index: 1565141 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.6381. Min Act: -0.1700

Data Index: 1591965 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.5756. Min Act: -0.1700

Data Index: 1573300 (Python Code)

Max Activating Token Index: 724

Text #9

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.6069. Min Act: -0.1700

Data Index: 1568550 (Python Code)

Max Activating Token Index: 494

Text #10

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.6069. Min Act: -0.1700

Data Index: 1605880 (Python Code)

Max Activating Token Index: 573

Text #11

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.6069. Min Act: -0.1700

Data Index: 1534698 (Python Code)

Max Activating Token Index: 426

Text #12

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.6069. Min Act: -0.1700

Data Index: 1489951 (Python Code)

Max Activating Token Index: 547

Text #13

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.5444. Min Act: -0.1700

Data Index: 1458920 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.5756. Min Act: -0.1700

Data Index: 1381076 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.5131. Min Act: -0.1700

Data Index: 1508322 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.4819. Min Act: -0.1700

Data Index: 1539674 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.4819. Min Act: -0.1700

Data Index: 1373931 (Python Code)

Max Activating Token Index: 555

Text #18

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.4819. Min Act: -0.1700

Data Index: 1482901 (Python Code)

Max Activating Token Index: 803

Text #19

Max Range: 5.7319. Min Range: -5.7319

Max Act: 5.4506. Min Act: -0.1700

Data Index: 1589295 (Python Code)

Max Activating Token Index: 284