Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1108 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.2858. Min Range: -3.2858

Max Act: 3.2858. Min Act: -0.1700

Data Index: 1512011 (Python Code)

Max Activating Token Index: 340

Text #1

Max Range: 3.2858. Min Range: -3.2858

Max Act: 3.2266. Min Act: -0.1700

Data Index: 1536520 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 3.2858. Min Range: -3.2858

Max Act: 3.1559. Min Act: -0.1700

Data Index: 1565988 (Python Code)

Max Activating Token Index: 400

Text #3

Max Range: 3.2858. Min Range: -3.2858

Max Act: 3.1217. Min Act: -0.1700

Data Index: 1537895 (Python Code)

Max Activating Token Index: 741

Text #4

Max Range: 3.2858. Min Range: -3.2858

Max Act: 3.0317. Min Act: -0.1700

Data Index: 1396730 (Python Code)

Max Activating Token Index: 976

Text #5

Max Range: 3.2858. Min Range: -3.2858

Max Act: 3.0114. Min Act: -0.1700

Data Index: 1574910 (Python Code)

Max Activating Token Index: 838

Text #6

Max Range: 3.2858. Min Range: -3.2858

Max Act: 3.0014. Min Act: -0.1700

Data Index: 366742 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9826. Min Act: -0.1700

Data Index: 1539610 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9861. Min Act: -0.1700

Data Index: 1636943 (Python Code)

Max Activating Token Index: 369

Text #9

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9705. Min Act: -0.1699

Data Index: 1564487 (Python Code)

Max Activating Token Index: 775

Text #10

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9656. Min Act: -0.1700

Data Index: 1643764 (Python Code)

Max Activating Token Index: 399

Text #11

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9478. Min Act: -0.1700

Data Index: 1460044 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9377. Min Act: -0.1700

Data Index: 1347503 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9443. Min Act: -0.1699

Data Index: 1651146 (Python Code)

Max Activating Token Index: 735

Text #14

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9215. Min Act: -0.1696

Data Index: 1525934 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9339. Min Act: -0.1696

Data Index: 1422014 (Python Code)

Max Activating Token Index: 182

Text #16

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9303. Min Act: -0.1700

Data Index: 1520472 (Python Code)

Max Activating Token Index: 92

Text #17

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9135. Min Act: -0.1700

Data Index: 1484119 (Python Code)

Max Activating Token Index: 844

Text #18

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.8913. Min Act: -0.1700

Data Index: 1606426 (Python Code)

Max Activating Token Index: 421

Text #19

Max Range: 3.2858. Min Range: -3.2858

Max Act: 2.9034. Min Act: -0.1700

Data Index: 653437 (C4 (Web Text))

Max Activating Token Index: 598