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

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

Neuron 1609 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: 2.9553. Min Range: -2.9553

Max Act: 2.9553. Min Act: -0.1700

Data Index: 552698 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.9494. Min Act: -0.1700

Data Index: 1043838 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.8858. Min Act: -0.1700

Data Index: 823687 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.8979. Min Act: -0.1700

Data Index: 983010 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.8812. Min Act: -0.1700

Data Index: 744018 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.8769. Min Act: -0.1700

Data Index: 1353826 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.8514. Min Act: -0.1700

Data Index: 725760 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.8309. Min Act: -0.1700

Data Index: 1320354 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7848. Min Act: -0.1700

Data Index: 367468 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7904. Min Act: -0.1700

Data Index: 68614 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7429. Min Act: -0.1700

Data Index: 1582560 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7491. Min Act: -0.1700

Data Index: 130370 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7216. Min Act: -0.1700

Data Index: 690107 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7602. Min Act: -0.1700

Data Index: 1177311 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7327. Min Act: -0.1700

Data Index: 162518 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7455. Min Act: -0.1700

Data Index: 1167645 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7512. Min Act: -0.1700

Data Index: 125020 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7569. Min Act: -0.1700

Data Index: 284936 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7156. Min Act: -0.1700

Data Index: 1084716 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 2.9553. Min Range: -2.9553

Max Act: 2.7208. Min Act: -0.1700

Data Index: 237973 (C4 (Web Text))

Max Activating Token Index: 584