Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 953 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.3001. Min Act: -0.1700

Data Index: 1043689 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.2372. Min Act: -0.1700

Data Index: 1329355 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.2215. Min Act: -0.1700

Data Index: 908958 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1900. Min Act: -0.1700

Data Index: 1012552 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1900. Min Act: -0.1700

Data Index: 1197271 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.2057. Min Act: -0.1700

Data Index: 1255159 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.2057. Min Act: -0.1700

Data Index: 390712 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1743. Min Act: -0.1700

Data Index: 1140444 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1585. Min Act: -0.1700

Data Index: 822054 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1743. Min Act: -0.1700

Data Index: 1003475 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1585. Min Act: -0.1700

Data Index: 1343077 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1270. Min Act: -0.1700

Data Index: 544824 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1743. Min Act: -0.1700

Data Index: 1295776 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1428. Min Act: -0.1700

Data Index: 930160 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1585. Min Act: -0.1700

Data Index: 671938 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1428. Min Act: -0.1700

Data Index: 629812 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1428. Min Act: -0.1700

Data Index: 402673 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1270. Min Act: -0.1700

Data Index: 817775 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1428. Min Act: -0.1700

Data Index: 75386 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1113. Min Act: -0.1700

Data Index: 741008 (C4 (Web Text))

Max Activating Token Index: 232