Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1058 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 11.0955. Min Range: -11.0955

Max Act: 11.0955. Min Act: -0.1700

Data Index: 116173 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.8455. Min Act: -0.1700

Data Index: 971338 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.7205. Min Act: -0.1700

Data Index: 432533 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.7205. Min Act: -0.1700

Data Index: 520936 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.4705. Min Act: -0.1700

Data Index: 615107 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.4705. Min Act: -0.1700

Data Index: 1071292 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.4705. Min Act: -0.1700

Data Index: 1245102 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.4705. Min Act: -0.1700

Data Index: 1265395 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.4705. Min Act: -0.1700

Data Index: 357725 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.5955. Min Act: -0.1700

Data Index: 457507 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.3455. Min Act: -0.1700

Data Index: 275493 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.4705. Min Act: -0.1700

Data Index: 1219332 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.3455. Min Act: -0.1700

Data Index: 415602 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.3455. Min Act: -0.1700

Data Index: 1029670 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.2205. Min Act: -0.1700

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.2205. Min Act: -0.1496

Data Index: 147505 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.3455. Min Act: -0.1700

Data Index: 950171 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.2205. Min Act: -0.1698

Data Index: 1022034 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.0955. Min Act: -0.1700

Data Index: 871550 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 11.0955. Min Range: -11.0955

Max Act: 10.2205. Min Act: -0.1700

Data Index: 619079 (C4 (Web Text))

Max Activating Token Index: 197