Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1684 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.2197. Min Range: -8.2197

Max Act: 8.2197. Min Act: -0.1700

Data Index: 25280 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 8.2197. Min Range: -8.2197

Max Act: 8.0947. Min Act: -0.1700

Data Index: 1257483 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.9384. Min Act: -0.1700

Data Index: 356208 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 8.2197. Min Range: -8.2197

Max Act: 8.0009. Min Act: -0.1700

Data Index: 593334 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 8.2197. Min Range: -8.2197

Max Act: 8.0009. Min Act: -0.1700

Data Index: 732406 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.8134. Min Act: -0.1700

Data Index: 278429 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 8.2197. Min Range: -8.2197

Max Act: 8.0009. Min Act: -0.1700

Data Index: 1044705 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.9072. Min Act: -0.1700

Data Index: 1182110 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.9072. Min Act: -0.1700

Data Index: 301264 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.8447. Min Act: -0.1700

Data Index: 686844 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.8447. Min Act: -0.1700

Data Index: 113832 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.7822. Min Act: -0.1700

Data Index: 1269134 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.8134. Min Act: -0.1700

Data Index: 842940 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.7197. Min Act: -0.1700

Data Index: 433219 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.7509. Min Act: -0.1700

Data Index: 722344 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.7509. Min Act: -0.1700

Data Index: 1034967 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.7197. Min Act: -0.1700

Data Index: 977840 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.6572. Min Act: -0.1700

Data Index: 1151010 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.7197. Min Act: -0.1700

Data Index: 439342 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 8.2197. Min Range: -8.2197

Max Act: 7.6572. Min Act: -0.1700

Data Index: 1131405 (C4 (Web Text))

Max Activating Token Index: 964