Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 343 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.6253. Min Act: -0.1700

Data Index: 944943 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5313. Min Act: -0.1699

Data Index: 403376 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5313. Min Act: -0.1699

Data Index: 982732 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5313. Min Act: -0.1700

Data Index: 898281 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5313. Min Act: -0.1700

Data Index: 22947 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5000. Min Act: -0.1700

Data Index: 432741 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4686. Min Act: -0.1700

Data Index: 1464595 (Python Code)

Max Activating Token Index: 324

Text #7

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4686. Min Act: -0.1700

Data Index: 266834 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4059. Min Act: -0.1700

Data Index: 5304 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3746. Min Act: -0.1700

Data Index: 97909 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3746. Min Act: -0.1700

Data Index: 1594954 (Python Code)

Max Activating Token Index: 235

Text #11

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3432. Min Act: -0.1700

Data Index: 1225975 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3432. Min Act: -0.1700

Data Index: 74472 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3432. Min Act: -0.1700

Data Index: 216647 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3118. Min Act: -0.1700

Data Index: 288425 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.2804. Min Act: -0.1700

Data Index: 821556 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3432. Min Act: -0.1700

Data Index: 1029235 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.2804. Min Act: -0.1700

Data Index: 1368929 (Python Code)

Max Activating Token Index: 298

Text #18

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.2804. Min Act: -0.1700

Data Index: 1505391 (Python Code)

Max Activating Token Index: 382

Text #19

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.2804. Min Act: -0.1700

Data Index: 1203557 (C4 (Web Text))

Max Activating Token Index: 914