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

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

Neuron 1934 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.8745. Min Act: -0.1700

Data Index: 1335835 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.8745. Min Act: -0.1700

Data Index: 983923 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.8120. Min Act: -0.1700

Data Index: 356518 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.7807. Min Act: -0.1700

Data Index: 1114418 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.7495. Min Act: -0.1700

Data Index: 181546 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.8120. Min Act: -0.1700

Data Index: 430957 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.7182. Min Act: -0.1700

Data Index: 194616 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.7182. Min Act: -0.1700

Data Index: 755304 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.6870. Min Act: -0.1700

Data Index: 160392 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.6870. Min Act: -0.1700

Data Index: 786396 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.6245. Min Act: -0.1700

Data Index: 737193 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.6557. Min Act: -0.1700

Data Index: 1127697 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.6870. Min Act: -0.1700

Data Index: 684568 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.5932. Min Act: -0.1700

Data Index: 84338 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.6557. Min Act: -0.1700

Data Index: 1139909 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.5932. Min Act: -0.1700

Data Index: 1234680 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.6245. Min Act: -0.1700

Data Index: 1070174 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.5620. Min Act: -0.1700

Data Index: 670948 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.5620. Min Act: -0.1700

Data Index: 811821 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 5.8745. Min Range: -5.8745

Max Act: 5.5620. Min Act: -0.1700

Data Index: 616070 (C4 (Web Text))

Max Activating Token Index: 937