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

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

Neuron 1013 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: 5.2956. Min Range: -5.2956

Max Act: 5.2956. Min Act: -0.1700

Data Index: 1133155 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 5.2956. Min Range: -5.2956

Max Act: 5.1081. Min Act: -0.1700

Data Index: 162877 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.9831. Min Act: -0.1700

Data Index: 251393 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 5.2956. Min Range: -5.2956

Max Act: 5.0143. Min Act: -0.1700

Data Index: 453493 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.9518. Min Act: -0.1700

Data Index: 645469 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.9518. Min Act: -0.1700

Data Index: 306364 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.9206. Min Act: -0.1700

Data Index: 1089105 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.9206. Min Act: -0.1700

Data Index: 1107555 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.8581. Min Act: -0.1700

Data Index: 257049 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.8893. Min Act: -0.1700

Data Index: 200924 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.8268. Min Act: -0.1700

Data Index: 1250082 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.7956. Min Act: -0.1700

Data Index: 1122356 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.7643. Min Act: -0.1700

Data Index: 906587 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.8268. Min Act: -0.1700

Data Index: 39708 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.7956. Min Act: -0.1700

Data Index: 580773 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.7956. Min Act: -0.1700

Data Index: 134764 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.7018. Min Act: -0.1700

Data Index: 1004896 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.7956. Min Act: -0.1700

Data Index: 139816 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.7643. Min Act: -0.1700

Data Index: 372331 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 5.2956. Min Range: -5.2956

Max Act: 4.7331. Min Act: -0.1700

Data Index: 65281 (C4 (Web Text))

Max Activating Token Index: 253