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

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

Neuron 1035 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.1792. Min Act: -0.1700

Data Index: 645672 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.1635. Min Act: -0.1700

Data Index: 591360 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.1635. Min Act: -0.1700

Data Index: 1550354 (Python Code)

Max Activating Token Index: 632

Text #3

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.1320. Min Act: -0.1700

Data Index: 532067 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.1320. Min Act: -0.1700

Data Index: 3207 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.1320. Min Act: -0.1700

Data Index: 710588 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.1477. Min Act: -0.1700

Data Index: 965730 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.1320. Min Act: -0.1700

Data Index: 1040250 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.1477. Min Act: -0.1700

Data Index: 461828 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.1162. Min Act: -0.1700

Data Index: 635270 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.0847. Min Act: -0.1700

Data Index: 210176 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.0689. Min Act: -0.1700

Data Index: 172316 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.0689. Min Act: -0.1700

Data Index: 640246 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.0373. Min Act: -0.1700

Data Index: 1376450 (Python Code)

Max Activating Token Index: 535

Text #14

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.0531. Min Act: -0.1700

Data Index: 57547 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.0531. Min Act: -0.1700

Data Index: 94561 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.0531. Min Act: -0.1700

Data Index: 612030 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.0531. Min Act: -0.1700

Data Index: 1284117 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.0373. Min Act: -0.1700

Data Index: 603178 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 3.1792. Min Range: -3.1792

Max Act: 3.0373. Min Act: -0.1699

Data Index: 852541 (C4 (Web Text))

Max Activating Token Index: 314