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

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

Neuron 1877 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.8943. Min Act: -0.1700

Data Index: 1179594 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.8630. Min Act: -0.1700

Data Index: 1258521 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.8630. Min Act: -0.1700

Data Index: 110770 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.8318. Min Act: -0.1700

Data Index: 1151394 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.8005. Min Act: -0.1700

Data Index: 1027423 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.8318. Min Act: -0.1700

Data Index: 244308 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.8318. Min Act: -0.1700

Data Index: 551124 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.8318. Min Act: -0.1700

Data Index: 1124188 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.8318. Min Act: -0.1700

Data Index: 684321 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.7692. Min Act: -0.1700

Data Index: 236648 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.7848. Min Act: -0.1700

Data Index: 941098 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.8318. Min Act: -0.1700

Data Index: 277765 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.7848. Min Act: -0.1700

Data Index: 50374 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.7536. Min Act: -0.1700

Data Index: 1293181 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.8005. Min Act: -0.1700

Data Index: 389311 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.7536. Min Act: -0.1700

Data Index: 245135 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.7379. Min Act: -0.1700

Data Index: 1248139 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.7536. Min Act: -0.1700

Data Index: 746573 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.7536. Min Act: -0.1700

Data Index: 947064 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 3.8943. Min Range: -3.8943

Max Act: 3.7536. Min Act: -0.1700

Data Index: 829895 (C4 (Web Text))

Max Activating Token Index: 672