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

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

Neuron 950 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: 4.0996. Min Range: -4.0996

Max Act: 4.0996. Min Act: -0.1700

Data Index: 1104908 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 4.0996. Min Range: -4.0996

Max Act: 4.0290. Min Act: -0.1700

Data Index: 1315036 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 4.0996. Min Range: -4.0996

Max Act: 4.0352. Min Act: -0.1700

Data Index: 206809 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 4.0996. Min Range: -4.0996

Max Act: 4.0182. Min Act: -0.1700

Data Index: 878013 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9969. Min Act: -0.1700

Data Index: 937632 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9918. Min Act: -0.1700

Data Index: 672738 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9920. Min Act: -0.1700

Data Index: 1345223 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 4.0996. Min Range: -4.0996

Max Act: 4.0017. Min Act: -0.1700

Data Index: 595323 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9658. Min Act: -0.1700

Data Index: 616633 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 4.0996. Min Range: -4.0996

Max Act: 4.0076. Min Act: -0.1700

Data Index: 135682 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9632. Min Act: -0.1699

Data Index: 9501 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9595. Min Act: -0.1700

Data Index: 327369 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9153. Min Act: -0.1700

Data Index: 290776 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9690. Min Act: -0.1700

Data Index: 14096 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9530. Min Act: -0.1700

Data Index: 420217 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9297. Min Act: -0.1700

Data Index: 1172377 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9578. Min Act: -0.1700

Data Index: 458884 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9190. Min Act: -0.1700

Data Index: 881867 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9240. Min Act: -0.1700

Data Index: 600383 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 4.0996. Min Range: -4.0996

Max Act: 3.9248. Min Act: -0.1700

Data Index: 1050365 (C4 (Web Text))

Max Activating Token Index: 291