Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1938 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1259. Min Range: -5.1259

Max Act: 5.1259. Min Act: -0.1700

Data Index: 919335 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 5.1259. Min Range: -5.1259

Max Act: 5.0947. Min Act: -0.1700

Data Index: 862299 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 5.1259. Min Range: -5.1259

Max Act: 5.0322. Min Act: -0.1700

Data Index: 17906 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 5.1259. Min Range: -5.1259

Max Act: 5.0634. Min Act: -0.1700

Data Index: 427672 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.9384. Min Act: -0.1700

Data Index: 1213964 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.8291. Min Act: -0.1699

Data Index: 319120 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.8291. Min Act: -0.1700

Data Index: 629796 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.9072. Min Act: -0.1700

Data Index: 440429 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.8134. Min Act: -0.1700

Data Index: 812615 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.7978. Min Act: -0.1700

Data Index: 1171476 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.7978. Min Act: -0.1700

Data Index: 720962 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.7822. Min Act: -0.1700

Data Index: 1103805 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.7978. Min Act: -0.1700

Data Index: 716176 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.7978. Min Act: -0.1700

Data Index: 1207785 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.7666. Min Act: -0.1700

Data Index: 1215606 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.7353. Min Act: -0.1700

Data Index: 987920 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.7197. Min Act: -0.1700

Data Index: 698173 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.7822. Min Act: -0.1700

Data Index: 1192748 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.7041. Min Act: -0.1700

Data Index: 969249 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.7041. Min Act: -0.1700

Data Index: 309966 (C4 (Web Text))

Max Activating Token Index: 948