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

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

Neuron 1245 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: 3.1263. Min Range: -3.1263

Max Act: 3.1263. Min Act: -0.1700

Data Index: 292772 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0948. Min Act: -0.1700

Data Index: 197010 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0632. Min Act: -0.1700

Data Index: 963900 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0948. Min Act: -0.1700

Data Index: 1046208 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0632. Min Act: -0.1700

Data Index: 674895 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0632. Min Act: -0.1700

Data Index: 668463 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0632. Min Act: -0.1700

Data Index: 343915 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0632. Min Act: -0.1700

Data Index: 998252 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0474. Min Act: -0.1700

Data Index: 337308 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0474. Min Act: -0.1700

Data Index: 980304 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0474. Min Act: -0.1700

Data Index: 1064594 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0317. Min Act: -0.1700

Data Index: 1346548 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0317. Min Act: -0.1700

Data Index: 675574 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0317. Min Act: -0.1700

Data Index: 931642 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0159. Min Act: -0.1700

Data Index: 480536 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0159. Min Act: -0.1700

Data Index: 504227 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0000. Min Act: -0.1700

Data Index: 211041 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 3.1263. Min Range: -3.1263

Max Act: 2.9842. Min Act: -0.1700

Data Index: 763233 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0000. Min Act: -0.1700

Data Index: 1168825 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 3.1263. Min Range: -3.1263

Max Act: 3.0000. Min Act: -0.1700

Data Index: 183124 (C4 (Web Text))

Max Activating Token Index: 579