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

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

Neuron 479 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.8148. Min Act: -0.1700

Data Index: 878232 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.6898. Min Act: -0.1700

Data Index: 598190 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.5023. Min Act: -0.1700

Data Index: 1099594 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.4711. Min Act: -0.1700

Data Index: 1217590 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.5023. Min Act: -0.1700

Data Index: 728660 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.3773. Min Act: -0.1700

Data Index: 299884 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.3461. Min Act: -0.1700

Data Index: 1118205 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.2836. Min Act: -0.1700

Data Index: 57458 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.3461. Min Act: -0.1700

Data Index: 872221 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.3148. Min Act: -0.1700

Data Index: 790563 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.3148. Min Act: -0.1700

Data Index: 570677 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.3148. Min Act: -0.1700

Data Index: 788935 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.3461. Min Act: -0.1700

Data Index: 1330500 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.2836. Min Act: -0.1700

Data Index: 1286266 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.2836. Min Act: -0.1700

Data Index: 794491 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.2836. Min Act: -0.1700

Data Index: 313860 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.2836. Min Act: -0.1700

Data Index: 1133458 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.2836. Min Act: -0.1700

Data Index: 1107301 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.2836. Min Act: -0.1700

Data Index: 1082656 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 5.8148. Min Range: -5.8148

Max Act: 5.2836. Min Act: -0.1700

Data Index: 840082 (C4 (Web Text))

Max Activating Token Index: 868