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

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

Neuron 1342 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: 5.2205. Min Range: -5.2205

Max Act: 5.2205. Min Act: -0.1700

Data Index: 1140649 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.2205. Min Act: -0.1700

Data Index: 700342 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.1112. Min Act: -0.1700

Data Index: 1199394 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.0643. Min Act: -0.1700

Data Index: 1096940 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.0955. Min Act: -0.1700

Data Index: 1051802 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.0643. Min Act: -0.1700

Data Index: 1271958 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.0330. Min Act: -0.1700

Data Index: 387610 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.0643. Min Act: -0.1700

Data Index: 781533 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.0018. Min Act: -0.1700

Data Index: 1323039 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 5.2205. Min Range: -5.2205

Max Act: 4.9861. Min Act: -0.1700

Data Index: 900191 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 5.2205. Min Range: -5.2205

Max Act: 4.9861. Min Act: -0.1700

Data Index: 408989 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.0018. Min Act: -0.1700

Data Index: 602546 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 5.2205. Min Range: -5.2205

Max Act: 4.9861. Min Act: -0.1700

Data Index: 197300 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.0174. Min Act: -0.1700

Data Index: 778684 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 5.2205. Min Range: -5.2205

Max Act: 4.9549. Min Act: -0.1700

Data Index: 876010 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 5.2205. Min Range: -5.2205

Max Act: 4.9705. Min Act: -0.1700

Data Index: 772381 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 5.2205. Min Range: -5.2205

Max Act: 4.9393. Min Act: -0.1700

Data Index: 1138670 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 5.2205. Min Range: -5.2205

Max Act: 4.9080. Min Act: -0.1700

Data Index: 861323 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 5.2205. Min Range: -5.2205

Max Act: 4.9549. Min Act: -0.1700

Data Index: 550647 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.0018. Min Act: -0.1700

Data Index: 576601 (C4 (Web Text))

Max Activating Token Index: 1011