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

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

Neuron 570 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: 2.9866. Min Range: -2.9866

Max Act: 2.9866. Min Act: -0.1700

Data Index: 30650 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.8743. Min Act: -0.1700

Data Index: 713991 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.8746. Min Act: -0.1700

Data Index: 442939 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.8685. Min Act: -0.1700

Data Index: 1044522 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.8488. Min Act: -0.1700

Data Index: 413680 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.8493. Min Act: -0.1700

Data Index: 279070 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.8412. Min Act: -0.1700

Data Index: 1118855 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.8364. Min Act: -0.1700

Data Index: 1234763 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.8236. Min Act: -0.1700

Data Index: 954682 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.8295. Min Act: -0.1700

Data Index: 494248 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.8291. Min Act: -0.1700

Data Index: 540721 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.7993. Min Act: -0.1700

Data Index: 1343250 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.8185. Min Act: -0.1700

Data Index: 741361 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.7930. Min Act: -0.1700

Data Index: 892441 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.7953. Min Act: -0.1700

Data Index: 1336593 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.7995. Min Act: -0.1700

Data Index: 822796 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.7960. Min Act: -0.1700

Data Index: 196481 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.7898. Min Act: -0.1700

Data Index: 1190693 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.7867. Min Act: -0.1700

Data Index: 267748 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 2.9866. Min Range: -2.9866

Max Act: 2.7749. Min Act: -0.1700

Data Index: 1204655 (C4 (Web Text))

Max Activating Token Index: 66