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

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

Neuron 1702 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.9925. Min Act: -0.1700

Data Index: 326503 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.9925. Min Act: -0.1700

Data Index: 1342316 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.9613. Min Act: -0.1700

Data Index: 173491 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.9300. Min Act: -0.1700

Data Index: 482549 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.9300. Min Act: -0.1700

Data Index: 914691 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8675. Min Act: -0.1700

Data Index: 396260 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8675. Min Act: -0.1700

Data Index: 1012067 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8675. Min Act: -0.1700

Data Index: 933958 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8363. Min Act: -0.1700

Data Index: 337365 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8050. Min Act: -0.1700

Data Index: 39237 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8363. Min Act: -0.1700

Data Index: 1283975 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8050. Min Act: -0.1700

Data Index: 780024 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8363. Min Act: -0.1700

Data Index: 662888 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8675. Min Act: -0.1700

Data Index: 463392 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8050. Min Act: -0.1700

Data Index: 898759 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8675. Min Act: -0.1700

Data Index: 204124 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8363. Min Act: -0.1700

Data Index: 753872 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.8050. Min Act: -0.1700

Data Index: 569043 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.7738. Min Act: -0.1700

Data Index: 1075822 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 4.9925. Min Range: -4.9925

Max Act: 4.7738. Min Act: -0.1700

Data Index: 645376 (C4 (Web Text))

Max Activating Token Index: 295