Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 485 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.5576. Min Act: -0.1700

Data Index: 4847401 (Open Web Text)

Max Activating Token Index: 211

Text #1

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.3935. Min Act: -0.1700

Data Index: 7881913 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.3543. Min Act: -0.1700

Data Index: 3282 (Open Web Text)

Max Activating Token Index: 469

Text #3

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.3083. Min Act: -0.1700

Data Index: 1351139 (Open Web Text)

Max Activating Token Index: 906

Text #4

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.2561. Min Act: -0.1700

Data Index: 4199410 (Open Web Text)

Max Activating Token Index: 135

Text #5

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.2474. Min Act: -0.1700

Data Index: 3787541 (Open Web Text)

Max Activating Token Index: 530

Text #6

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.2557. Min Act: -0.1700

Data Index: 7171478 (Open Web Text)

Max Activating Token Index: 488

Text #7

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.2171. Min Act: -0.1700

Data Index: 4964105 (Open Web Text)

Max Activating Token Index: 883

Text #8

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.2208. Min Act: -0.1700

Data Index: 2121910 (Open Web Text)

Max Activating Token Index: 126

Text #9

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.2460. Min Act: -0.1700

Data Index: 8774425 (Open Web Text)

Max Activating Token Index: 359

Text #10

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.1833. Min Act: -0.1700

Data Index: 7401687 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.1870. Min Act: -0.1700

Data Index: 6592529 (Open Web Text)

Max Activating Token Index: 790

Text #12

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.1922. Min Act: -0.1700

Data Index: 8102732 (Open Web Text)

Max Activating Token Index: 362

Text #13

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.2137. Min Act: -0.1700

Data Index: 5242186 (Open Web Text)

Max Activating Token Index: 731

Text #14

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.1548. Min Act: -0.1700

Data Index: 6511409 (Open Web Text)

Max Activating Token Index: 290

Text #15

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.1801. Min Act: -0.1700

Data Index: 1593393 (Open Web Text)

Max Activating Token Index: 693

Text #16

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.1632. Min Act: -0.1700

Data Index: 6945810 (Open Web Text)

Max Activating Token Index: 401

Text #17

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.2078. Min Act: -0.1700

Data Index: 4680689 (Open Web Text)

Max Activating Token Index: 660

Text #18

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.1872. Min Act: -0.1700

Data Index: 7887156 (Open Web Text)

Max Activating Token Index: 504

Text #19

Max Range: 4.5576. Min Range: -4.5576

Max Act: 4.2550. Min Act: -0.1700

Data Index: 747803 (Open Web Text)

Max Activating Token Index: 788