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

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

Neuron 376 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: 3.0559. Min Range: -3.0559

Max Act: 3.0559. Min Act: -0.1700

Data Index: 1312615 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 3.0559. Min Range: -3.0559

Max Act: 3.0055. Min Act: -0.1700

Data Index: 272917 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 3.0559. Min Range: -3.0559

Max Act: 3.0121. Min Act: -0.1700

Data Index: 183317 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.9992. Min Act: -0.1700

Data Index: 361953 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.9587. Min Act: -0.1700

Data Index: 758304 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.9194. Min Act: -0.1700

Data Index: 873541 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.9212. Min Act: -0.1700

Data Index: 30889 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8857. Min Act: -0.1700

Data Index: 1635429 (Python Code)

Max Activating Token Index: 221

Text #8

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8766. Min Act: -0.1700

Data Index: 971864 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8797. Min Act: -0.1700

Data Index: 1160539 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8684. Min Act: -0.1700

Data Index: 1034743 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8605. Min Act: -0.1700

Data Index: 551352 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8707. Min Act: -0.1700

Data Index: 415546 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8756. Min Act: -0.1700

Data Index: 382912 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8639. Min Act: -0.1700

Data Index: 1324130 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8753. Min Act: -0.1700

Data Index: 448073 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8582. Min Act: -0.1700

Data Index: 1572953 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8672. Min Act: -0.1700

Data Index: 1619120 (Python Code)

Max Activating Token Index: 896

Text #18

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8652. Min Act: -0.1700

Data Index: 980945 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8597. Min Act: -0.1700

Data Index: 1314949 (C4 (Web Text))

Max Activating Token Index: 911