Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1797 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.9868. Min Act: -0.1700

Data Index: 1084369 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.9555. Min Act: -0.1700

Data Index: 942954 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.8930. Min Act: -0.1700

Data Index: 1005953 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.8930. Min Act: -0.1700

Data Index: 701371 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.7992. Min Act: -0.1700

Data Index: 597061 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.7679. Min Act: -0.1700

Data Index: 882817 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.7679. Min Act: -0.1700

Data Index: 1034882 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.7366. Min Act: -0.1700

Data Index: 680112 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.7366. Min Act: -0.1700

Data Index: 1186941 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.7053. Min Act: -0.1700

Data Index: 1052204 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.7366. Min Act: -0.1700

Data Index: 708587 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.7053. Min Act: -0.1700

Data Index: 78922 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.7366. Min Act: -0.1700

Data Index: 1344643 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.7053. Min Act: -0.1700

Data Index: 987953 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.7053. Min Act: -0.1700

Data Index: 652309 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.6740. Min Act: -0.1700

Data Index: 511578 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.6740. Min Act: -0.1700

Data Index: 845180 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.6427. Min Act: -0.1700

Data Index: 1178833 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.6740. Min Act: -0.1700

Data Index: 870684 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 3.9868. Min Range: -3.9868

Max Act: 3.6740. Min Act: -0.1700

Data Index: 628343 (C4 (Web Text))

Max Activating Token Index: 135