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

Dataset: Open Web Text

Neuron 2965 in Layer 4

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: 5.2066. Min Range: -5.2066

Max Act: 5.2066. Min Act: -0.1700

Data Index: 707137 (Open Web Text)

Max Activating Token Index: 307

Text #1

Max Range: 5.2066. Min Range: -5.2066

Max Act: 5.1514. Min Act: -0.1700

Data Index: 8158315 (Open Web Text)

Max Activating Token Index: 347

Text #2

Max Range: 5.2066. Min Range: -5.2066

Max Act: 5.1260. Min Act: -0.1700

Data Index: 3292461 (Open Web Text)

Max Activating Token Index: 130

Text #3

Max Range: 5.2066. Min Range: -5.2066

Max Act: 5.1233. Min Act: -0.1700

Data Index: 8467834 (Open Web Text)

Max Activating Token Index: 686

Text #4

Max Range: 5.2066. Min Range: -5.2066

Max Act: 5.1151. Min Act: -0.1700

Data Index: 2400512 (Open Web Text)

Max Activating Token Index: 126

Text #5

Max Range: 5.2066. Min Range: -5.2066

Max Act: 5.0315. Min Act: -0.1700

Data Index: 4628219 (Open Web Text)

Max Activating Token Index: 399

Text #6

Max Range: 5.2066. Min Range: -5.2066

Max Act: 5.0586. Min Act: -0.1700

Data Index: 5030219 (Open Web Text)

Max Activating Token Index: 1009

Text #7

Max Range: 5.2066. Min Range: -5.2066

Max Act: 4.9935. Min Act: -0.1700

Data Index: 8462522 (Open Web Text)

Max Activating Token Index: 496

Text #8

Max Range: 5.2066. Min Range: -5.2066

Max Act: 5.0502. Min Act: -0.1700

Data Index: 8459921 (Open Web Text)

Max Activating Token Index: 793

Text #9

Max Range: 5.2066. Min Range: -5.2066

Max Act: 5.0256. Min Act: -0.1700

Data Index: 8330108 (Open Web Text)

Max Activating Token Index: 533

Text #10

Max Range: 5.2066. Min Range: -5.2066

Max Act: 5.0187. Min Act: -0.1700

Data Index: 7637999 (Open Web Text)

Max Activating Token Index: 926

Text #11

Max Range: 5.2066. Min Range: -5.2066

Max Act: 4.9824. Min Act: -0.1700

Data Index: 3489796 (Open Web Text)

Max Activating Token Index: 828

Text #12

Max Range: 5.2066. Min Range: -5.2066

Max Act: 4.9773. Min Act: -0.1700

Data Index: 3529778 (Open Web Text)

Max Activating Token Index: 470

Text #13

Max Range: 5.2066. Min Range: -5.2066

Max Act: 5.0244. Min Act: -0.1700

Data Index: 8220843 (Open Web Text)

Max Activating Token Index: 749

Text #14

Max Range: 5.2066. Min Range: -5.2066

Max Act: 4.9377. Min Act: -0.1700

Data Index: 6137 (Open Web Text)

Max Activating Token Index: 628

Text #15

Max Range: 5.2066. Min Range: -5.2066

Max Act: 4.9521. Min Act: -0.1700

Data Index: 4032456 (Open Web Text)

Max Activating Token Index: 336

Text #16

Max Range: 5.2066. Min Range: -5.2066

Max Act: 4.9703. Min Act: -0.1700

Data Index: 2143853 (Open Web Text)

Max Activating Token Index: 633

Text #17

Max Range: 5.2066. Min Range: -5.2066

Max Act: 4.9480. Min Act: -0.1700

Data Index: 319039 (Open Web Text)

Max Activating Token Index: 964

Text #18

Max Range: 5.2066. Min Range: -5.2066

Max Act: 4.9245. Min Act: -0.1700

Data Index: 2771890 (Open Web Text)

Max Activating Token Index: 100

Text #19

Max Range: 5.2066. Min Range: -5.2066

Max Act: 4.9100. Min Act: -0.1700

Data Index: 2442255 (Open Web Text)

Max Activating Token Index: 579