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

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

Neuron 1281 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.6195. Min Act: -0.1700

Data Index: 82980 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.4315. Min Act: -0.1700

Data Index: 1276081 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.3374. Min Act: -0.1700

Data Index: 1000697 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.3060. Min Act: -0.1700

Data Index: 213965 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2903. Min Act: -0.1700

Data Index: 32127 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2903. Min Act: -0.1700

Data Index: 399685 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2903. Min Act: -0.1700

Data Index: 1292694 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2903. Min Act: -0.1700

Data Index: 394845 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2274. Min Act: -0.1700

Data Index: 692342 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2746. Min Act: -0.1700

Data Index: 435011 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.3060. Min Act: -0.1700

Data Index: 1242539 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2589. Min Act: -0.1700

Data Index: 709114 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2274. Min Act: -0.1700

Data Index: 279931 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2589. Min Act: -0.1700

Data Index: 1256043 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2274. Min Act: -0.1700

Data Index: 745144 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.1960. Min Act: -0.1700

Data Index: 309820 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.1960. Min Act: -0.1700

Data Index: 571238 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.1803. Min Act: -0.1700

Data Index: 1170961 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2117. Min Act: -0.1700

Data Index: 1105509 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 3.6195. Min Range: -3.6195

Max Act: 3.2274. Min Act: -0.1700

Data Index: 452275 (C4 (Web Text))

Max Activating Token Index: 946