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

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

Neuron 1963 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: 3.6105. Min Range: -3.6105

Max Act: 3.6105. Min Act: -0.1700

Data Index: 1056840 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.5792. Min Act: -0.1700

Data Index: 507799 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.5166. Min Act: -0.1700

Data Index: 1006843 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.4852. Min Act: -0.1700

Data Index: 1068833 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.4695. Min Act: -0.1700

Data Index: 17734 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.4539. Min Act: -0.1700

Data Index: 1434930 (Python Code)

Max Activating Token Index: 978

Text #6

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.4225. Min Act: -0.1700

Data Index: 507445 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.3911. Min Act: -0.1700

Data Index: 1209977 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.3911. Min Act: -0.1700

Data Index: 97980 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.3911. Min Act: -0.1700

Data Index: 839274 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.4225. Min Act: -0.1700

Data Index: 1235615 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.3911. Min Act: -0.1700

Data Index: 1080290 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.4225. Min Act: -0.1700

Data Index: 418719 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.4068. Min Act: -0.1700

Data Index: 1226401 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.3755. Min Act: -0.1700

Data Index: 697093 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.3755. Min Act: -0.1700

Data Index: 1076225 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.4068. Min Act: -0.1700

Data Index: 47191 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.4068. Min Act: -0.1700

Data Index: 414188 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.3911. Min Act: -0.1700

Data Index: 832120 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.3755. Min Act: -0.1700

Data Index: 251003 (C4 (Web Text))

Max Activating Token Index: 47