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

Dataset: Open Web Text

Neuron 2221 in Layer 2

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: 1.7315. Min Range: -1.7315

Max Act: 1.7315. Min Act: -0.1700

Data Index: 2495932 (Open Web Text)

Max Activating Token Index: 795

Text #1

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.5842. Min Act: -0.1700

Data Index: 6789422 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.5627. Min Act: -0.1700

Data Index: 428550 (Open Web Text)

Max Activating Token Index: 442

Text #3

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.5646. Min Act: -0.1700

Data Index: 4437692 (Open Web Text)

Max Activating Token Index: 879

Text #4

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.5084. Min Act: -0.1700

Data Index: 601365 (Open Web Text)

Max Activating Token Index: 48

Text #5

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4981. Min Act: -0.1700

Data Index: 1047365 (Open Web Text)

Max Activating Token Index: 413

Text #6

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.5214. Min Act: -0.1700

Data Index: 1143301 (Open Web Text)

Max Activating Token Index: 92

Text #7

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4800. Min Act: -0.1700

Data Index: 1910829 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4797. Min Act: -0.1700

Data Index: 5950326 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4967. Min Act: -0.1700

Data Index: 1585343 (Open Web Text)

Max Activating Token Index: 91

Text #10

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4894. Min Act: -0.1700

Data Index: 4592591 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4425. Min Act: -0.1700

Data Index: 7896147 (Open Web Text)

Max Activating Token Index: 320

Text #12

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4797. Min Act: -0.1700

Data Index: 4678577 (Open Web Text)

Max Activating Token Index: 185

Text #13

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4701. Min Act: -0.1700

Data Index: 344189 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4556. Min Act: -0.1700

Data Index: 1434007 (Open Web Text)

Max Activating Token Index: 575

Text #15

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4650. Min Act: -0.1700

Data Index: 4822887 (Open Web Text)

Max Activating Token Index: 372

Text #16

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4463. Min Act: -0.1700

Data Index: 2096463 (Open Web Text)

Max Activating Token Index: 501

Text #17

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4688. Min Act: -0.1700

Data Index: 1647986 (Open Web Text)

Max Activating Token Index: 33

Text #18

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4620. Min Act: -0.1700

Data Index: 38030 (Open Web Text)

Max Activating Token Index: 215

Text #19

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4439. Min Act: -0.1700

Data Index: 4678352 (Open Web Text)

Max Activating Token Index: 103