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

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

Neuron 1850 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.8038. Min Act: -0.1700

Data Index: 70763 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.7726. Min Act: -0.1700

Data Index: 523797 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.7413. Min Act: -0.1700

Data Index: 410668 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.7100. Min Act: -0.1700

Data Index: 325014 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.7100. Min Act: -0.1700

Data Index: 308753 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6474. Min Act: -0.1700

Data Index: 224239 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6787. Min Act: -0.1700

Data Index: 1288106 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6787. Min Act: -0.1700

Data Index: 718275 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6474. Min Act: -0.1700

Data Index: 190045 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6474. Min Act: -0.1700

Data Index: 405744 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6161. Min Act: -0.1700

Data Index: 1157262 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6474. Min Act: -0.1700

Data Index: 506627 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6474. Min Act: -0.1700

Data Index: 551440 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.5848. Min Act: -0.1700

Data Index: 1149672 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6161. Min Act: -0.1700

Data Index: 461955 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6161. Min Act: -0.1700

Data Index: 1002998 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6161. Min Act: -0.1700

Data Index: 943920 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6474. Min Act: -0.1700

Data Index: 1262509 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.6161. Min Act: -0.1700

Data Index: 587776 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 3.8038. Min Range: -3.8038

Max Act: 3.5534. Min Act: -0.1700

Data Index: 895818 (C4 (Web Text))

Max Activating Token Index: 772