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

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

Neuron 1517 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: 3.4139. Min Range: -3.4139

Max Act: 3.4139. Min Act: -0.1700

Data Index: 1089661 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3982. Min Act: -0.1700

Data Index: 249793 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3982. Min Act: -0.1700

Data Index: 1041154 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3825. Min Act: -0.1700

Data Index: 926383 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3825. Min Act: -0.1700

Data Index: 918306 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3668. Min Act: -0.1700

Data Index: 915908 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3825. Min Act: -0.1700

Data Index: 75004 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3511. Min Act: -0.1700

Data Index: 1041576 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3668. Min Act: -0.1700

Data Index: 304876 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3668. Min Act: -0.1700

Data Index: 210899 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3511. Min Act: -0.1700

Data Index: 43144 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3355. Min Act: -0.1700

Data Index: 631300 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3355. Min Act: -0.1700

Data Index: 92862 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3668. Min Act: -0.1700

Data Index: 850578 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3355. Min Act: -0.1700

Data Index: 841600 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3511. Min Act: -0.1700

Data Index: 503978 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3355. Min Act: -0.1700

Data Index: 824084 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3355. Min Act: -0.1700

Data Index: 393615 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3355. Min Act: -0.1700

Data Index: 689486 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 3.4139. Min Range: -3.4139

Max Act: 3.3355. Min Act: -0.1700

Data Index: 644027 (C4 (Web Text))

Max Activating Token Index: 876