Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1061 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.2915. Min Act: -0.1700

Data Index: 26664 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.2601. Min Act: -0.1700

Data Index: 753987 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.2444. Min Act: -0.1700

Data Index: 1611106 (Python Code)

Max Activating Token Index: 888

Text #3

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.2129. Min Act: -0.1700

Data Index: 1075733 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1972. Min Act: -0.1700

Data Index: 240635 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1815. Min Act: -0.1700

Data Index: 1509618 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1815. Min Act: -0.1700

Data Index: 319823 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1815. Min Act: -0.1700

Data Index: 558435 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1657. Min Act: -0.1700

Data Index: 1353324 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1815. Min Act: -0.1700

Data Index: 71283 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1815. Min Act: -0.1700

Data Index: 1223992 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1500. Min Act: -0.1700

Data Index: 724635 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1500. Min Act: -0.1700

Data Index: 892948 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1500. Min Act: -0.1700

Data Index: 1005245 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1500. Min Act: -0.1700

Data Index: 72918 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1342. Min Act: -0.1700

Data Index: 683045 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1500. Min Act: -0.1700

Data Index: 998170 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1342. Min Act: -0.1700

Data Index: 338780 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1185. Min Act: -0.1700

Data Index: 466925 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1342. Min Act: -0.1700

Data Index: 868821 (C4 (Web Text))

Max Activating Token Index: 545