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

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

Neuron 331 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.4797. Min Act: -0.1700

Data Index: 1137482 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.4797. Min Act: -0.1700

Data Index: 560408 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.3860. Min Act: -0.1700

Data Index: 371848 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.3860. Min Act: -0.1700

Data Index: 1234556 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.3860. Min Act: -0.1700

Data Index: 76969 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.3860. Min Act: -0.1700

Data Index: 676785 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.3547. Min Act: -0.1700

Data Index: 533431 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.3547. Min Act: -0.1700

Data Index: 1045197 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.3547. Min Act: -0.1700

Data Index: 265366 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.2610. Min Act: -0.1700

Data Index: 1273231 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.3235. Min Act: -0.1700

Data Index: 1099228 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.3547. Min Act: -0.1700

Data Index: 85266 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.2922. Min Act: -0.1700

Data Index: 381551 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.2297. Min Act: -0.1700

Data Index: 46661 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.2610. Min Act: -0.1700

Data Index: 1079263 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.2610. Min Act: -0.1700

Data Index: 657309 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.2610. Min Act: -0.1700

Data Index: 204769 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.2922. Min Act: -0.1700

Data Index: 763695 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.2297. Min Act: -0.1700

Data Index: 41733 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 5.4797. Min Range: -5.4797

Max Act: 5.2297. Min Act: -0.1700

Data Index: 678058 (C4 (Web Text))

Max Activating Token Index: 575