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

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

Neuron 1647 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.8164. Min Act: -0.1700

Data Index: 253569 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7851. Min Act: -0.1700

Data Index: 1492506 (Python Code)

Max Activating Token Index: 365

Text #2

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.8164. Min Act: -0.1700

Data Index: 1570258 (Python Code)

Max Activating Token Index: 180

Text #3

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7851. Min Act: -0.1700

Data Index: 924632 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7851. Min Act: -0.1700

Data Index: 1627013 (Python Code)

Max Activating Token Index: 950

Text #5

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7538. Min Act: -0.1700

Data Index: 1469329 (Python Code)

Max Activating Token Index: 208

Text #6

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7538. Min Act: -0.1700

Data Index: 1491658 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7538. Min Act: -0.1700

Data Index: 568718 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7538. Min Act: -0.1700

Data Index: 270829 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7225. Min Act: -0.1700

Data Index: 264171 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7225. Min Act: -0.1700

Data Index: 1393228 (Python Code)

Max Activating Token Index: 412

Text #11

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7225. Min Act: -0.1700

Data Index: 1027511 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.6599. Min Act: -0.1700

Data Index: 280187 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.6912. Min Act: -0.1700

Data Index: 473957 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7225. Min Act: -0.1700

Data Index: 1021828 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.6599. Min Act: -0.1700

Data Index: 472262 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.6599. Min Act: -0.1700

Data Index: 891144 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.6286. Min Act: -0.1700

Data Index: 1043073 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.6599. Min Act: -0.1700

Data Index: 1643800 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.6286. Min Act: -0.1700

Data Index: 1615878 (Python Code)

Max Activating Token Index: 238