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

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

Neuron 1559 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.2488. Min Act: -0.1700

Data Index: 388296 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.2312. Min Act: -0.1700

Data Index: 759573 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.2136. Min Act: -0.1700

Data Index: 556009 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1959. Min Act: -0.1700

Data Index: 390958 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1959. Min Act: -0.1700

Data Index: 1210193 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1871. Min Act: -0.1700

Data Index: 876092 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1871. Min Act: -0.1700

Data Index: 325260 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1871. Min Act: -0.1700

Data Index: 210811 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1871. Min Act: -0.1700

Data Index: 1091090 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1871. Min Act: -0.1700

Data Index: 1034882 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1871. Min Act: -0.1700

Data Index: 222896 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1783. Min Act: -0.1700

Data Index: 1147703 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1783. Min Act: -0.1699

Data Index: 582340 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1783. Min Act: -0.1700

Data Index: 333972 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1783. Min Act: -0.1700

Data Index: 975942 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1783. Min Act: -0.1700

Data Index: 612356 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1695. Min Act: -0.1700

Data Index: 760644 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1783. Min Act: -0.1700

Data Index: 782545 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1695. Min Act: -0.1700

Data Index: 831346 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 1.2488. Min Range: -1.2488

Max Act: 1.1783. Min Act: -0.1700

Data Index: 802216 (C4 (Web Text))

Max Activating Token Index: 10