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

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

Neuron 1138 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: 3.8631. Min Range: -3.8631

Max Act: 3.8631. Min Act: -0.1700

Data Index: 152956 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.8395. Min Act: -0.1700

Data Index: 285721 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7965. Min Act: -0.1700

Data Index: 226266 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.8113. Min Act: -0.1700

Data Index: 876521 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7665. Min Act: -0.1700

Data Index: 141307 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7801. Min Act: -0.1700

Data Index: 157020 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7831. Min Act: -0.1700

Data Index: 118049 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7300. Min Act: -0.1700

Data Index: 284492 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7285. Min Act: -0.1700

Data Index: 178113 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7218. Min Act: -0.1700

Data Index: 844785 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6966. Min Act: -0.1700

Data Index: 1005332 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6906. Min Act: -0.1700

Data Index: 254019 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7085. Min Act: -0.1700

Data Index: 710835 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7159. Min Act: -0.1700

Data Index: 877533 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6675. Min Act: -0.1700

Data Index: 861890 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6799. Min Act: -0.1700

Data Index: 544493 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6862. Min Act: -0.1700

Data Index: 520087 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6727. Min Act: -0.1700

Data Index: 302132 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6772. Min Act: -0.1700

Data Index: 580850 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6801. Min Act: -0.1700

Data Index: 384855 (C4 (Web Text))

Max Activating Token Index: 12