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

Dataset: Open Web Text

Neuron 1795 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: 3.7263. Min Range: -3.7263

Max Act: 3.7263. Min Act: -0.1700

Data Index: 6762761 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.7050. Min Act: -0.1700

Data Index: 6241379 (Open Web Text)

Max Activating Token Index: 547

Text #2

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.6419. Min Act: -0.1700

Data Index: 589167 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.6585. Min Act: -0.1700

Data Index: 8677146 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.6386. Min Act: -0.1700

Data Index: 1971658 (Open Web Text)

Max Activating Token Index: 87

Text #5

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.6333. Min Act: -0.1700

Data Index: 487334 (Open Web Text)

Max Activating Token Index: 123

Text #6

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.6314. Min Act: -0.1700

Data Index: 644984 (Open Web Text)

Max Activating Token Index: 918

Text #7

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.5892. Min Act: -0.1700

Data Index: 5493630 (Open Web Text)

Max Activating Token Index: 492

Text #8

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.6034. Min Act: -0.1700

Data Index: 5007187 (Open Web Text)

Max Activating Token Index: 479

Text #9

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.5883. Min Act: -0.1700

Data Index: 3537648 (Open Web Text)

Max Activating Token Index: 677

Text #10

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.6003. Min Act: -0.1700

Data Index: 5989616 (Open Web Text)

Max Activating Token Index: 439

Text #11

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.5883. Min Act: -0.1700

Data Index: 5728303 (Open Web Text)

Max Activating Token Index: 82

Text #12

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.5885. Min Act: -0.1700

Data Index: 2440973 (Open Web Text)

Max Activating Token Index: 357

Text #13

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.5888. Min Act: -0.1700

Data Index: 4686026 (Open Web Text)

Max Activating Token Index: 481

Text #14

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.6042. Min Act: -0.1700

Data Index: 2017485 (Open Web Text)

Max Activating Token Index: 621

Text #15

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.6028. Min Act: -0.1700

Data Index: 1729669 (Open Web Text)

Max Activating Token Index: 688

Text #16

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.5829. Min Act: -0.1700

Data Index: 1150216 (Open Web Text)

Max Activating Token Index: 942

Text #17

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.5662. Min Act: -0.1700

Data Index: 4589841 (Open Web Text)

Max Activating Token Index: 66

Text #18

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.5905. Min Act: -0.1700

Data Index: 814077 (Open Web Text)

Max Activating Token Index: 707

Text #19

Max Range: 3.7263. Min Range: -3.7263

Max Act: 3.5804. Min Act: -0.1700

Data Index: 127296 (Open Web Text)

Max Activating Token Index: 179