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

Dataset: Open Web Text

Neuron 1032 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: 4.0605. Min Range: -4.0605

Max Act: 4.0471. Min Act: -0.1700

Data Index: 6686231 (Open Web Text)

Max Activating Token Index: 582

Text #1

Max Range: 4.0605. Min Range: -4.0605

Max Act: 4.0605. Min Act: -0.1700

Data Index: 3698289 (Open Web Text)

Max Activating Token Index: 958

Text #2

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9753. Min Act: -0.1700

Data Index: 3119197 (Open Web Text)

Max Activating Token Index: 79

Text #3

Max Range: 4.0605. Min Range: -4.0605

Max Act: 4.0050. Min Act: -0.1700

Data Index: 1037285 (Open Web Text)

Max Activating Token Index: 857

Text #4

Max Range: 4.0605. Min Range: -4.0605

Max Act: 4.0176. Min Act: -0.1700

Data Index: 6694998 (Open Web Text)

Max Activating Token Index: 73

Text #5

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9656. Min Act: -0.1700

Data Index: 532301 (Open Web Text)

Max Activating Token Index: 277

Text #6

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9257. Min Act: -0.1700

Data Index: 6002847 (Open Web Text)

Max Activating Token Index: 561

Text #7

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9328. Min Act: -0.1700

Data Index: 8561474 (Open Web Text)

Max Activating Token Index: 785

Text #8

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9390. Min Act: -0.1700

Data Index: 3416234 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9216. Min Act: -0.1700

Data Index: 5883274 (Open Web Text)

Max Activating Token Index: 813

Text #10

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9320. Min Act: -0.1700

Data Index: 3181517 (Open Web Text)

Max Activating Token Index: 226

Text #11

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9048. Min Act: -0.1700

Data Index: 8611950 (Open Web Text)

Max Activating Token Index: 136

Text #12

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9002. Min Act: -0.1700

Data Index: 34732 (Open Web Text)

Max Activating Token Index: 43

Text #13

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9198. Min Act: -0.1700

Data Index: 503006 (Open Web Text)

Max Activating Token Index: 464

Text #14

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9002. Min Act: -0.1700

Data Index: 8228460 (Open Web Text)

Max Activating Token Index: 504

Text #15

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9068. Min Act: -0.1700

Data Index: 270185 (Open Web Text)

Max Activating Token Index: 976

Text #16

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8567. Min Act: -0.1700

Data Index: 8016287 (Open Web Text)

Max Activating Token Index: 354

Text #17

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8567. Min Act: -0.1700

Data Index: 6186991 (Open Web Text)

Max Activating Token Index: 991

Text #18

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8896. Min Act: -0.1700

Data Index: 6042207 (Open Web Text)

Max Activating Token Index: 480

Text #19

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8264. Min Act: -0.1700

Data Index: 1400087 (Open Web Text)

Max Activating Token Index: 900