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

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

Neuron 437 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.2446. Min Act: -0.1700

Data Index: 927834 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1974. Min Act: -0.1700

Data Index: 1171226 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.0240. Min Act: -0.1700

Data Index: 971799 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.0398. Min Act: -0.1700

Data Index: 427323 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.0082. Min Act: -0.1700

Data Index: 768454 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.9924. Min Act: -0.1700

Data Index: 250371 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.0082. Min Act: -0.1700

Data Index: 1056486 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.0240. Min Act: -0.1700

Data Index: 67894 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.0082. Min Act: -0.1700

Data Index: 110065 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.9924. Min Act: -0.1700

Data Index: 1450407 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.9765. Min Act: -0.1700

Data Index: 810744 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.9607. Min Act: -0.1700

Data Index: 160167 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.9449. Min Act: -0.1700

Data Index: 1202571 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.9765. Min Act: -0.1700

Data Index: 1064645 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.9449. Min Act: -0.1700

Data Index: 803384 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.9607. Min Act: -0.1700

Data Index: 1654117 (Python Code)

Max Activating Token Index: 871

Text #16

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.9290. Min Act: -0.1700

Data Index: 65829 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.8973. Min Act: -0.1700

Data Index: 700454 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.9290. Min Act: -0.1700

Data Index: 1479027 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 3.2446. Min Range: -3.2446

Max Act: 2.8973. Min Act: -0.1700

Data Index: 154322 (C4 (Web Text))

Max Activating Token Index: 672