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

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

Neuron 1143 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.2987. Min Act: -0.1700

Data Index: 656657 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.2673. Min Act: -0.1700

Data Index: 266078 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.2201. Min Act: -0.1700

Data Index: 219804 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.2358. Min Act: -0.1700

Data Index: 1129547 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.2044. Min Act: -0.1700

Data Index: 1338845 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.1729. Min Act: -0.1700

Data Index: 1325704 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.2358. Min Act: -0.1700

Data Index: 1103282 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.1887. Min Act: -0.1700

Data Index: 260334 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.2044. Min Act: -0.1700

Data Index: 1315727 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.1414. Min Act: -0.1700

Data Index: 1412298 (Python Code)

Max Activating Token Index: 860

Text #10

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.0941. Min Act: -0.1700

Data Index: 1590151 (Python Code)

Max Activating Token Index: 876

Text #11

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.1414. Min Act: -0.1700

Data Index: 1577541 (Python Code)

Max Activating Token Index: 758

Text #12

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.1414. Min Act: -0.1700

Data Index: 1550921 (Python Code)

Max Activating Token Index: 287

Text #13

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.1257. Min Act: -0.1700

Data Index: 1519293 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.1414. Min Act: -0.1700

Data Index: 663714 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.1414. Min Act: -0.1700

Data Index: 1034424 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.1257. Min Act: -0.1700

Data Index: 753809 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.1099. Min Act: -0.1700

Data Index: 123791 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.0784. Min Act: -0.1700

Data Index: 230372 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 3.2987. Min Range: -3.2987

Max Act: 3.0784. Min Act: -0.1700

Data Index: 984493 (C4 (Web Text))

Max Activating Token Index: 788