Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1625 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.6224. Min Act: -0.1700

Data Index: 54254 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.5598. Min Act: -0.1700

Data Index: 1343827 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.5598. Min Act: -0.1700

Data Index: 108888 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.5128. Min Act: -0.1700

Data Index: 359468 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4815. Min Act: -0.1700

Data Index: 152857 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4971. Min Act: -0.1700

Data Index: 975652 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4501. Min Act: -0.1700

Data Index: 795914 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4344. Min Act: -0.1700

Data Index: 566611 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4187. Min Act: -0.1700

Data Index: 1197245 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4187. Min Act: -0.1700

Data Index: 877591 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4031. Min Act: -0.1700

Data Index: 1291937 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4031. Min Act: -0.1700

Data Index: 857210 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4031. Min Act: -0.1700

Data Index: 567637 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3717. Min Act: -0.1700

Data Index: 594753 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3560. Min Act: -0.1700

Data Index: 224263 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3717. Min Act: -0.1700

Data Index: 379065 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3874. Min Act: -0.1700

Data Index: 688351 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3560. Min Act: -0.1700

Data Index: 744973 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3560. Min Act: -0.1700

Data Index: 415074 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3717. Min Act: -0.1700

Data Index: 862571 (C4 (Web Text))

Max Activating Token Index: 375