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

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

Neuron 561 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: 3.2635. Min Range: -3.2635

Max Act: 3.2635. Min Act: -0.1700

Data Index: 324494 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.2046. Min Act: -0.1700

Data Index: 622091 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.1967. Min Act: -0.1700

Data Index: 905162 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.1519. Min Act: -0.1700

Data Index: 733504 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.1479. Min Act: -0.1700

Data Index: 1619236 (Python Code)

Max Activating Token Index: 888

Text #5

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.1213. Min Act: -0.1700

Data Index: 1271658 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.1430. Min Act: -0.1700

Data Index: 1335054 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.1037. Min Act: -0.1700

Data Index: 869297 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0943. Min Act: -0.1700

Data Index: 850297 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0896. Min Act: -0.1700

Data Index: 1596123 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0769. Min Act: -0.1700

Data Index: 1217898 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0850. Min Act: -0.1700

Data Index: 172435 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0757. Min Act: -0.1700

Data Index: 960543 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0533. Min Act: -0.1700

Data Index: 661342 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0512. Min Act: -0.1700

Data Index: 711378 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0407. Min Act: -0.1700

Data Index: 1161595 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0507. Min Act: -0.1700

Data Index: 1160085 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0385. Min Act: -0.1700

Data Index: 221261 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0293. Min Act: -0.1700

Data Index: 1424539 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 3.2635. Min Range: -3.2635

Max Act: 3.0392. Min Act: -0.1700

Data Index: 1352022 (C4 (Web Text))

Max Activating Token Index: 807