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

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

Neuron 993 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: 4.1951. Min Range: -4.1951

Max Act: 4.1951. Min Act: -0.1700

Data Index: 1485622 (Python Code)

Max Activating Token Index: 423

Text #1

Max Range: 4.1951. Min Range: -4.1951

Max Act: 4.1804. Min Act: -0.1700

Data Index: 635804 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 4.1951. Min Range: -4.1951

Max Act: 4.0316. Min Act: -0.1698

Data Index: 1538696 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 4.1951. Min Range: -4.1951

Max Act: 4.0227. Min Act: -0.1700

Data Index: 1186370 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 4.1951. Min Range: -4.1951

Max Act: 4.0153. Min Act: -0.1700

Data Index: 1510462 (Python Code)

Max Activating Token Index: 542

Text #5

Max Range: 4.1951. Min Range: -4.1951

Max Act: 4.0156. Min Act: -0.1700

Data Index: 1535441 (Python Code)

Max Activating Token Index: 979

Text #6

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.9934. Min Act: -0.1700

Data Index: 1514347 (Python Code)

Max Activating Token Index: 654

Text #7

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.9658. Min Act: -0.1697

Data Index: 1590325 (Python Code)

Max Activating Token Index: 943

Text #8

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8987. Min Act: -0.1697

Data Index: 936507 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.9012. Min Act: -0.1700

Data Index: 177887 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8766. Min Act: -0.1700

Data Index: 436050 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8430. Min Act: -0.1700

Data Index: 363182 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8588. Min Act: -0.1698

Data Index: 1533166 (Python Code)

Max Activating Token Index: 848

Text #13

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8585. Min Act: -0.1700

Data Index: 1582049 (Python Code)

Max Activating Token Index: 400

Text #14

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8583. Min Act: -0.1697

Data Index: 1426101 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8500. Min Act: -0.1699

Data Index: 1571669 (Python Code)

Max Activating Token Index: 955

Text #16

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8617. Min Act: -0.1698

Data Index: 1412126 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8620. Min Act: -0.1700

Data Index: 1496784 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8414. Min Act: -0.1700

Data Index: 1624010 (Python Code)

Max Activating Token Index: 537

Text #19

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8494. Min Act: -0.1697

Data Index: 1389829 (Python Code)

Max Activating Token Index: 259