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

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

Neuron 777 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: 5.2870. Min Range: -5.2870

Max Act: 5.2870. Min Act: -0.1700

Data Index: 954761 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.2557. Min Act: -0.1700

Data Index: 1293228 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1620. Min Act: -0.1700

Data Index: 1072064 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1307. Min Act: -0.1700

Data Index: 1194521 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.0370. Min Act: -0.1700

Data Index: 1116593 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.0370. Min Act: -0.1700

Data Index: 520451 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.0057. Min Act: -0.1700

Data Index: 1110027 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.0057. Min Act: -0.1700

Data Index: 986515 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.9120. Min Act: -0.1700

Data Index: 261745 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.9120. Min Act: -0.1700

Data Index: 204996 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.8495. Min Act: -0.1700

Data Index: 1324549 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.8182. Min Act: -0.1700

Data Index: 247669 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.8182. Min Act: -0.1700

Data Index: 481866 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.8182. Min Act: -0.1700

Data Index: 498342 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.8807. Min Act: -0.1700

Data Index: 812534 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.7870. Min Act: -0.1700

Data Index: 631832 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.8495. Min Act: -0.1700

Data Index: 1304298 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.7557. Min Act: -0.1700

Data Index: 90989 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.7557. Min Act: -0.1700

Data Index: 226761 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 5.2870. Min Range: -5.2870

Max Act: 4.7870. Min Act: -0.1700

Data Index: 323480 (C4 (Web Text))

Max Activating Token Index: 737