Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 268 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.3133. Min Range: -4.3133

Max Act: 4.3133. Min Act: -0.1700

Data Index: 1409385 (Python Code)

Max Activating Token Index: 972

Text #1

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.9382. Min Act: -0.1700

Data Index: 1371338 (Python Code)

Max Activating Token Index: 265

Text #2

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.8131. Min Act: -0.1700

Data Index: 1391307 (Python Code)

Max Activating Token Index: 667

Text #3

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.8756. Min Act: -0.1700

Data Index: 1598578 (Python Code)

Max Activating Token Index: 653

Text #4

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.8443. Min Act: -0.1700

Data Index: 1432715 (Python Code)

Max Activating Token Index: 1020

Text #5

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.8131. Min Act: -0.1700

Data Index: 1644023 (Python Code)

Max Activating Token Index: 154

Text #6

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.7505. Min Act: -0.1700

Data Index: 1397507 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.7192. Min Act: -0.1700

Data Index: 1468985 (Python Code)

Max Activating Token Index: 764

Text #8

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.6879. Min Act: -0.1699

Data Index: 1370774 (Python Code)

Max Activating Token Index: 669

Text #9

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.6566. Min Act: -0.1700

Data Index: 1622382 (Python Code)

Max Activating Token Index: 550

Text #10

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.6879. Min Act: -0.1700

Data Index: 1447140 (Python Code)

Max Activating Token Index: 723

Text #11

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.6879. Min Act: -0.1700

Data Index: 1510795 (Python Code)

Max Activating Token Index: 909

Text #12

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.7192. Min Act: -0.1700

Data Index: 979522 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.6566. Min Act: -0.1700

Data Index: 1502614 (Python Code)

Max Activating Token Index: 616

Text #14

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.6253. Min Act: -0.1700

Data Index: 1648026 (Python Code)

Max Activating Token Index: 124

Text #15

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.6253. Min Act: -0.1694

Data Index: 1099302 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.6253. Min Act: -0.1700

Data Index: 1480309 (Python Code)

Max Activating Token Index: 561

Text #17

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.6253. Min Act: -0.1700

Data Index: 1379503 (Python Code)

Max Activating Token Index: 990

Text #18

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.6253. Min Act: -0.1700

Data Index: 1562715 (Python Code)

Max Activating Token Index: 443

Text #19

Max Range: 4.3133. Min Range: -4.3133

Max Act: 3.6253. Min Act: -0.1700

Data Index: 599727 (C4 (Web Text))

Max Activating Token Index: 514