Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 521 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.7170. Min Act: -0.1700

Data Index: 1320722 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.5920. Min Act: -0.1700

Data Index: 1183288 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.5295. Min Act: -0.1700

Data Index: 565094 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.6545. Min Act: -0.1700

Data Index: 213996 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.6545. Min Act: -0.1700

Data Index: 146139 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.5920. Min Act: -0.1700

Data Index: 443242 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.5920. Min Act: -0.1700

Data Index: 1273650 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.5920. Min Act: -0.1700

Data Index: 13386 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.5295. Min Act: -0.1700

Data Index: 640580 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.4982. Min Act: -0.1700

Data Index: 229878 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.4982. Min Act: -0.1700

Data Index: 377695 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.4982. Min Act: -0.1700

Data Index: 599360 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.6545. Min Act: -0.1700

Data Index: 625048 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.5295. Min Act: -0.1700

Data Index: 90373 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.4670. Min Act: -0.1700

Data Index: 26122 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.5295. Min Act: -0.1700

Data Index: 106103 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.4982. Min Act: -0.1700

Data Index: 555918 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.4670. Min Act: -0.1700

Data Index: 102282 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.4670. Min Act: -0.1700

Data Index: 725843 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 8.7170. Min Range: -8.7170

Max Act: 8.4357. Min Act: -0.1700

Data Index: 1068614 (C4 (Web Text))

Max Activating Token Index: 820