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

Dataset: Open Web Text

Neuron 1266 in Layer 5

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: 3.8786. Min Range: -3.8786

Max Act: 3.8786. Min Act: -0.1700

Data Index: 2900013 (Open Web Text)

Max Activating Token Index: 950

Text #1

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.7557. Min Act: -0.1700

Data Index: 1104752 (Open Web Text)

Max Activating Token Index: 932

Text #2

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6644. Min Act: -0.1700

Data Index: 8315985 (Open Web Text)

Max Activating Token Index: 615

Text #3

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.6062. Min Act: -0.1700

Data Index: 1114209 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5797. Min Act: -0.1700

Data Index: 5131856 (Open Web Text)

Max Activating Token Index: 531

Text #5

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5794. Min Act: -0.1700

Data Index: 2254763 (Open Web Text)

Max Activating Token Index: 533

Text #6

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5338. Min Act: -0.1700

Data Index: 5972920 (Open Web Text)

Max Activating Token Index: 418

Text #7

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5388. Min Act: -0.1700

Data Index: 314716 (Open Web Text)

Max Activating Token Index: 364

Text #8

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5535. Min Act: -0.1700

Data Index: 2845261 (Open Web Text)

Max Activating Token Index: 1005

Text #9

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5517. Min Act: -0.1700

Data Index: 2378339 (Open Web Text)

Max Activating Token Index: 212

Text #10

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5562. Min Act: -0.1700

Data Index: 6363206 (Open Web Text)

Max Activating Token Index: 459

Text #11

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5416. Min Act: -0.1700

Data Index: 6059652 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5390. Min Act: -0.1700

Data Index: 5706432 (Open Web Text)

Max Activating Token Index: 31

Text #13

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5274. Min Act: -0.1700

Data Index: 8039941 (Open Web Text)

Max Activating Token Index: 951

Text #14

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5164. Min Act: -0.1700

Data Index: 1891918 (Open Web Text)

Max Activating Token Index: 560

Text #15

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5214. Min Act: -0.1700

Data Index: 4262099 (Open Web Text)

Max Activating Token Index: 920

Text #16

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5174. Min Act: -0.1700

Data Index: 4732966 (Open Web Text)

Max Activating Token Index: 266

Text #17

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5273. Min Act: -0.1700

Data Index: 7516396 (Open Web Text)

Max Activating Token Index: 138

Text #18

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5461. Min Act: -0.1700

Data Index: 6809885 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.5172. Min Act: -0.1700

Data Index: 6817957 (Open Web Text)

Max Activating Token Index: 324