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

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

Neuron 1843 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.3773. Min Act: -0.1700

Data Index: 179769 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.3460. Min Act: -0.1700

Data Index: 254023 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.3460. Min Act: -0.1700

Data Index: 328261 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.2523. Min Act: -0.1700

Data Index: 254864 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.1585. Min Act: -0.1700

Data Index: 691213 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.1898. Min Act: -0.1700

Data Index: 1305860 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.2210. Min Act: -0.1700

Data Index: 624687 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.1898. Min Act: -0.1700

Data Index: 1175731 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.1585. Min Act: -0.1700

Data Index: 962454 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.1585. Min Act: -0.1700

Data Index: 766474 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.0960. Min Act: -0.1700

Data Index: 1243152 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.1585. Min Act: -0.1700

Data Index: 848380 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.0960. Min Act: -0.1700

Data Index: 975380 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.0335. Min Act: -0.1700

Data Index: 449246 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.0960. Min Act: -0.1700

Data Index: 1082933 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 5.3773. Min Range: -5.3773

Max Act: 4.9710. Min Act: -0.1700

Data Index: 840288 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 5.3773. Min Range: -5.3773

Max Act: 5.0023. Min Act: -0.1700

Data Index: 129129 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 5.3773. Min Range: -5.3773

Max Act: 4.9710. Min Act: -0.1700

Data Index: 1058559 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 5.3773. Min Range: -5.3773

Max Act: 4.9398. Min Act: -0.1700

Data Index: 27344 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 5.3773. Min Range: -5.3773

Max Act: 4.9710. Min Act: -0.1700

Data Index: 1064072 (C4 (Web Text))

Max Activating Token Index: 901