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

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

Neuron 2002 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: 3.3129. Min Range: -3.3129

Max Act: 3.2972. Min Act: -0.1700

Data Index: 97114 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2501. Min Act: -0.1700

Data Index: 1335297 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2815. Min Act: -0.1700

Data Index: 1089164 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2501. Min Act: -0.1700

Data Index: 590522 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2186. Min Act: -0.1700

Data Index: 1362759 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2343. Min Act: -0.1700

Data Index: 1393958 (Python Code)

Max Activating Token Index: 739

Text #6

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.3129. Min Act: -0.1700

Data Index: 1544264 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2343. Min Act: -0.1700

Data Index: 46347 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2343. Min Act: -0.1700

Data Index: 1249960 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2029. Min Act: -0.1700

Data Index: 1212559 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1557. Min Act: -0.1700

Data Index: 786162 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2186. Min Act: -0.1700

Data Index: 955608 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2186. Min Act: -0.1700

Data Index: 1476092 (Python Code)

Max Activating Token Index: 479

Text #13

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2343. Min Act: -0.1700

Data Index: 1606693 (Python Code)

Max Activating Token Index: 657

Text #14

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1714. Min Act: -0.1700

Data Index: 1291907 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2029. Min Act: -0.1700

Data Index: 38091 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1714. Min Act: -0.1700

Data Index: 912718 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2343. Min Act: -0.1700

Data Index: 359067 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1872. Min Act: -0.1700

Data Index: 748056 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1557. Min Act: -0.1700

Data Index: 84469 (C4 (Web Text))

Max Activating Token Index: 962