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

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

Neuron 366 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: 5.6468. Min Range: -5.6468

Max Act: 5.6468. Min Act: -0.1700

Data Index: 187099 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.6156. Min Act: -0.1700

Data Index: 606819 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.3968. Min Act: -0.1700

Data Index: 1101634 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.3656. Min Act: -0.1700

Data Index: 64132 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.3656. Min Act: -0.1700

Data Index: 1351264 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.3656. Min Act: -0.1700

Data Index: 1340886 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.3343. Min Act: -0.1700

Data Index: 690961 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.3343. Min Act: -0.1700

Data Index: 1186798 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.3343. Min Act: -0.1700

Data Index: 293991 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.3656. Min Act: -0.1700

Data Index: 161574 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.3656. Min Act: -0.1700

Data Index: 1247821 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.2718. Min Act: -0.1700

Data Index: 307309 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.3343. Min Act: -0.1700

Data Index: 1121871 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.2406. Min Act: -0.1700

Data Index: 170255 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.2406. Min Act: -0.1700

Data Index: 712681 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.2093. Min Act: -0.1700

Data Index: 1239007 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.1781. Min Act: -0.1700

Data Index: 1258307 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.2093. Min Act: -0.1700

Data Index: 659074 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.1468. Min Act: -0.1700

Data Index: 461676 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 5.6468. Min Range: -5.6468

Max Act: 5.1468. Min Act: -0.1700

Data Index: 187904 (C4 (Web Text))

Max Activating Token Index: 1017