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

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

Neuron 507 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: 3.7169. Min Range: -3.7169

Max Act: 3.7169. Min Act: -0.1700

Data Index: 41701 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.6230. Min Act: -0.1700

Data Index: 1302848 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.5917. Min Act: -0.1700

Data Index: 1287599 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.5917. Min Act: -0.1700

Data Index: 1337705 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.5604. Min Act: -0.1700

Data Index: 787625 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4977. Min Act: -0.1700

Data Index: 300684 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.5291. Min Act: -0.1700

Data Index: 185646 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.5291. Min Act: -0.1700

Data Index: 1020241 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4977. Min Act: -0.1700

Data Index: 381584 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4664. Min Act: -0.1700

Data Index: 815 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4664. Min Act: -0.1700

Data Index: 1285843 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4664. Min Act: -0.1700

Data Index: 739114 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4350. Min Act: -0.1700

Data Index: 823485 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4664. Min Act: -0.1700

Data Index: 1335193 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4664. Min Act: -0.1700

Data Index: 1277137 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4037. Min Act: -0.1700

Data Index: 916377 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4350. Min Act: -0.1700

Data Index: 901653 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4350. Min Act: -0.1700

Data Index: 780652 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4977. Min Act: -0.1700

Data Index: 1040783 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.4664. Min Act: -0.1700

Data Index: 624960 (C4 (Web Text))

Max Activating Token Index: 69