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

Dataset: Open Web Text

Neuron 1064 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: 5.9363. Min Range: -5.9363

Max Act: 5.9363. Min Act: -0.1700

Data Index: 3065455 (Open Web Text)

Max Activating Token Index: 238

Text #1

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.7782. Min Act: -0.1700

Data Index: 223268 (Open Web Text)

Max Activating Token Index: 608

Text #2

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.8001. Min Act: -0.1700

Data Index: 6359744 (Open Web Text)

Max Activating Token Index: 187

Text #3

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.8140. Min Act: -0.1700

Data Index: 5227341 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.7443. Min Act: -0.1700

Data Index: 1486596 (Open Web Text)

Max Activating Token Index: 992

Text #5

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.7844. Min Act: -0.1700

Data Index: 7966996 (Open Web Text)

Max Activating Token Index: 609

Text #6

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.6681. Min Act: -0.1700

Data Index: 2737028 (Open Web Text)

Max Activating Token Index: 481

Text #7

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.7095. Min Act: -0.1700

Data Index: 6623137 (Open Web Text)

Max Activating Token Index: 193

Text #8

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.6657. Min Act: -0.1700

Data Index: 3876370 (Open Web Text)

Max Activating Token Index: 810

Text #9

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.6179. Min Act: -0.1700

Data Index: 813418 (Open Web Text)

Max Activating Token Index: 428

Text #10

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.5651. Min Act: -0.1700

Data Index: 5116384 (Open Web Text)

Max Activating Token Index: 202

Text #11

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.5682. Min Act: -0.1700

Data Index: 2684454 (Open Web Text)

Max Activating Token Index: 845

Text #12

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.4736. Min Act: -0.1700

Data Index: 4781231 (Open Web Text)

Max Activating Token Index: 460

Text #13

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.5584. Min Act: -0.1700

Data Index: 1725890 (Open Web Text)

Max Activating Token Index: 640

Text #14

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.4563. Min Act: -0.1700

Data Index: 8142687 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.5185. Min Act: -0.1700

Data Index: 2944262 (Open Web Text)

Max Activating Token Index: 952

Text #16

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.4755. Min Act: -0.1700

Data Index: 1764501 (Open Web Text)

Max Activating Token Index: 930

Text #17

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.5272. Min Act: -0.1700

Data Index: 7000858 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.4921. Min Act: -0.1700

Data Index: 5145396 (Open Web Text)

Max Activating Token Index: 671

Text #19

Max Range: 5.9363. Min Range: -5.9363

Max Act: 5.4957. Min Act: -0.1700

Data Index: 2802044 (Open Web Text)

Max Activating Token Index: 308