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

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

Neuron 1513 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.6872. Min Act: -0.1700

Data Index: 357419 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.6560. Min Act: -0.1700

Data Index: 1122632 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.5935. Min Act: -0.1700

Data Index: 1098316 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.5622. Min Act: -0.1700

Data Index: 498601 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.4997. Min Act: -0.1700

Data Index: 361133 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.4685. Min Act: -0.1700

Data Index: 1020316 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.4997. Min Act: -0.1700

Data Index: 30898 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.4060. Min Act: -0.1700

Data Index: 486704 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.4060. Min Act: -0.1700

Data Index: 277813 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.4060. Min Act: -0.1700

Data Index: 1090770 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.4685. Min Act: -0.1700

Data Index: 124432 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.3747. Min Act: -0.1700

Data Index: 1209293 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.4060. Min Act: -0.1700

Data Index: 1275718 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.3747. Min Act: -0.1700

Data Index: 1338882 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.4060. Min Act: -0.1700

Data Index: 1066390 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.4060. Min Act: -0.1699

Data Index: 457587 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.3747. Min Act: -0.1700

Data Index: 1184825 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.3122. Min Act: -0.1700

Data Index: 1184538 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.3435. Min Act: -0.1700

Data Index: 846466 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 5.6872. Min Range: -5.6872

Max Act: 5.3435. Min Act: -0.1700

Data Index: 695291 (C4 (Web Text))

Max Activating Token Index: 292