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

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

Neuron 390 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: 3.1154. Min Range: -3.1154

Max Act: 3.1154. Min Act: -0.1700

Data Index: 1550994 (Python Code)

Max Activating Token Index: 347

Text #1

Max Range: 3.1154. Min Range: -3.1154

Max Act: 3.0049. Min Act: -0.1700

Data Index: 1551543 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 3.1154. Min Range: -3.1154

Max Act: 3.0049. Min Act: -0.1700

Data Index: 1592326 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9733. Min Act: -0.1700

Data Index: 1369961 (Python Code)

Max Activating Token Index: 53

Text #4

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9416. Min Act: -0.1700

Data Index: 1475682 (Python Code)

Max Activating Token Index: 190

Text #5

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9258. Min Act: -0.1700

Data Index: 1548663 (Python Code)

Max Activating Token Index: 407

Text #6

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9099. Min Act: -0.1700

Data Index: 1494837 (Python Code)

Max Activating Token Index: 1005

Text #7

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9099. Min Act: -0.1700

Data Index: 1635686 (Python Code)

Max Activating Token Index: 176

Text #8

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.8941. Min Act: -0.1700

Data Index: 1366082 (Python Code)

Max Activating Token Index: 129

Text #9

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.8941. Min Act: -0.1700

Data Index: 1461085 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.8941. Min Act: -0.1700

Data Index: 1345339 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.8623. Min Act: -0.1700

Data Index: 1574368 (Python Code)

Max Activating Token Index: 529

Text #12

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.8464. Min Act: -0.1700

Data Index: 1611356 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.8146. Min Act: -0.1700

Data Index: 1619682 (Python Code)

Max Activating Token Index: 698

Text #14

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.7987. Min Act: -0.1700

Data Index: 1373188 (Python Code)

Max Activating Token Index: 301

Text #15

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.7987. Min Act: -0.1700

Data Index: 1572610 (Python Code)

Max Activating Token Index: 322

Text #16

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.7987. Min Act: -0.1700

Data Index: 1622346 (Python Code)

Max Activating Token Index: 875

Text #17

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.8146. Min Act: -0.1700

Data Index: 1502273 (Python Code)

Max Activating Token Index: 684

Text #18

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.7828. Min Act: -0.1700

Data Index: 877508 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.7987. Min Act: -0.1700

Data Index: 1558910 (Python Code)

Max Activating Token Index: 162