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

Dataset: Open Web Text

Neuron 1084 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: 4.2031. Min Range: -4.2031

Max Act: 4.2031. Min Act: -0.1700

Data Index: 6563182 (Open Web Text)

Max Activating Token Index: 827

Text #1

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1430. Min Act: -0.1700

Data Index: 5542092 (Open Web Text)

Max Activating Token Index: 590

Text #2

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1004. Min Act: -0.1700

Data Index: 593426 (Open Web Text)

Max Activating Token Index: 482

Text #3

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1179. Min Act: -0.1700

Data Index: 8563102 (Open Web Text)

Max Activating Token Index: 517

Text #4

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0816. Min Act: -0.1700

Data Index: 1080306 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0692. Min Act: -0.1700

Data Index: 7621126 (Open Web Text)

Max Activating Token Index: 677

Text #6

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0447. Min Act: -0.1700

Data Index: 2752846 (Open Web Text)

Max Activating Token Index: 631

Text #7

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0416. Min Act: -0.1700

Data Index: 2290071 (Open Web Text)

Max Activating Token Index: 664

Text #8

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0702. Min Act: -0.1700

Data Index: 4542519 (Open Web Text)

Max Activating Token Index: 605

Text #9

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0615. Min Act: -0.1700

Data Index: 399939 (Open Web Text)

Max Activating Token Index: 348

Text #10

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0761. Min Act: -0.1700

Data Index: 4367138 (Open Web Text)

Max Activating Token Index: 402

Text #11

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0377. Min Act: -0.1700

Data Index: 945520 (Open Web Text)

Max Activating Token Index: 249

Text #12

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0310. Min Act: -0.1700

Data Index: 2907177 (Open Web Text)

Max Activating Token Index: 835

Text #13

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0026. Min Act: -0.1700

Data Index: 2251653 (Open Web Text)

Max Activating Token Index: 883

Text #14

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0215. Min Act: -0.1700

Data Index: 7867508 (Open Web Text)

Max Activating Token Index: 744

Text #15

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0032. Min Act: -0.1700

Data Index: 3487473 (Open Web Text)

Max Activating Token Index: 429

Text #16

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0284. Min Act: -0.1700

Data Index: 3390336 (Open Web Text)

Max Activating Token Index: 1010

Text #17

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0178. Min Act: -0.1700

Data Index: 6798036 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 4.2031. Min Range: -4.2031

Max Act: 3.9882. Min Act: -0.1700

Data Index: 6860368 (Open Web Text)

Max Activating Token Index: 473

Text #19

Max Range: 4.2031. Min Range: -4.2031

Max Act: 3.9996. Min Act: -0.1700

Data Index: 4148091 (Open Web Text)

Max Activating Token Index: 216