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

Dataset: Open Web Text

Neuron 2256 in Layer 3

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: 4.1012. Min Range: -4.1012

Max Act: 4.1012. Min Act: -0.1700

Data Index: 5648469 (Open Web Text)

Max Activating Token Index: 633

Text #1

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.9909. Min Act: -0.1700

Data Index: 323656 (Open Web Text)

Max Activating Token Index: 813

Text #2

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.9675. Min Act: -0.1700

Data Index: 4171454 (Open Web Text)

Max Activating Token Index: 451

Text #3

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.9290. Min Act: -0.1700

Data Index: 8221173 (Open Web Text)

Max Activating Token Index: 615

Text #4

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.9645. Min Act: -0.1700

Data Index: 323657 (Open Web Text)

Max Activating Token Index: 626

Text #5

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.9076. Min Act: -0.1700

Data Index: 540210 (Open Web Text)

Max Activating Token Index: 582

Text #6

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.8272. Min Act: -0.1700

Data Index: 4171455 (Open Web Text)

Max Activating Token Index: 563

Text #7

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.8735. Min Act: -0.1700

Data Index: 4171462 (Open Web Text)

Max Activating Token Index: 72

Text #8

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.8459. Min Act: -0.1700

Data Index: 4171466 (Open Web Text)

Max Activating Token Index: 158

Text #9

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.8312. Min Act: -0.1700

Data Index: 8353502 (Open Web Text)

Max Activating Token Index: 372

Text #10

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.8452. Min Act: -0.1700

Data Index: 5536214 (Open Web Text)

Max Activating Token Index: 919

Text #11

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.7878. Min Act: -0.1700

Data Index: 6163504 (Open Web Text)

Max Activating Token Index: 366

Text #12

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.8259. Min Act: -0.1700

Data Index: 3079974 (Open Web Text)

Max Activating Token Index: 570

Text #13

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.8316. Min Act: -0.1700

Data Index: 4171452 (Open Web Text)

Max Activating Token Index: 339

Text #14

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.7326. Min Act: -0.1700

Data Index: 6881091 (Open Web Text)

Max Activating Token Index: 442

Text #15

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.7982. Min Act: -0.1700

Data Index: 1135330 (Open Web Text)

Max Activating Token Index: 354

Text #16

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.7948. Min Act: -0.1700

Data Index: 6419717 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.8108. Min Act: -0.1700

Data Index: 3604064 (Open Web Text)

Max Activating Token Index: 559

Text #18

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.8033. Min Act: -0.1700

Data Index: 2477273 (Open Web Text)

Max Activating Token Index: 214

Text #19

Max Range: 4.1012. Min Range: -4.1012

Max Act: 3.7846. Min Act: -0.1700

Data Index: 1864416 (Open Web Text)

Max Activating Token Index: 96