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

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

Neuron 1179 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.9551. Min Act: -0.1700

Data Index: 1093282 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.8926. Min Act: -0.1700

Data Index: 726368 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.8926. Min Act: -0.1700

Data Index: 871209 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.8926. Min Act: -0.1700

Data Index: 679897 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.8926. Min Act: -0.1700

Data Index: 1330274 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.7364. Min Act: -0.1700

Data Index: 797793 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.8301. Min Act: -0.1700

Data Index: 814943 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.7364. Min Act: -0.1700

Data Index: 939258 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.7051. Min Act: -0.1700

Data Index: 1286583 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.7051. Min Act: -0.1700

Data Index: 770157 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.7676. Min Act: -0.1700

Data Index: 177575 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.6739. Min Act: -0.1700

Data Index: 350905 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.7051. Min Act: -0.1700

Data Index: 974372 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.7051. Min Act: -0.1700

Data Index: 1100135 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.6739. Min Act: -0.1700

Data Index: 1312797 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.6739. Min Act: -0.1700

Data Index: 831988 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.7364. Min Act: -0.1700

Data Index: 1146212 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.6739. Min Act: -0.1700

Data Index: 944044 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.6114. Min Act: -0.1700

Data Index: 738213 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 5.9551. Min Range: -5.9551

Max Act: 5.7051. Min Act: -0.1700

Data Index: 1242491 (C4 (Web Text))

Max Activating Token Index: 609