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

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

Neuron 1906 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: 5.4314. Min Range: -5.4314

Max Act: 5.4001. Min Act: -0.1700

Data Index: 726531 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.4314. Min Act: -0.1700

Data Index: 218928 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.3689. Min Act: -0.1700

Data Index: 847313 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.3689. Min Act: -0.1700

Data Index: 1314412 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.3064. Min Act: -0.1700

Data Index: 229283 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.3064. Min Act: -0.1700

Data Index: 985835 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.2751. Min Act: -0.1700

Data Index: 1219421 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.2439. Min Act: -0.1700

Data Index: 1307957 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.2751. Min Act: -0.1700

Data Index: 560363 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.2751. Min Act: -0.1700

Data Index: 865984 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.1814. Min Act: -0.1700

Data Index: 65224 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.2751. Min Act: -0.1700

Data Index: 755352 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.2439. Min Act: -0.1700

Data Index: 291345 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.2126. Min Act: -0.1700

Data Index: 387797 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.2439. Min Act: -0.1700

Data Index: 1067698 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.1814. Min Act: -0.1700

Data Index: 12476 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.1814. Min Act: -0.1700

Data Index: 704653 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.1814. Min Act: -0.1700

Data Index: 277697 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.1814. Min Act: -0.1700

Data Index: 1143020 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 5.4314. Min Range: -5.4314

Max Act: 5.1189. Min Act: -0.1700

Data Index: 877166 (C4 (Web Text))

Max Activating Token Index: 327