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

Dataset: Open Web Text

Neuron 2217 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: 4.0292. Min Range: -4.0292

Max Act: 4.0171. Min Act: -0.1700

Data Index: 1287824 (Open Web Text)

Max Activating Token Index: 964

Text #1

Max Range: 4.0292. Min Range: -4.0292

Max Act: 4.0292. Min Act: -0.1700

Data Index: 3739895 (Open Web Text)

Max Activating Token Index: 124

Text #2

Max Range: 4.0292. Min Range: -4.0292

Max Act: 4.0096. Min Act: -0.1700

Data Index: 5526453 (Open Web Text)

Max Activating Token Index: 416

Text #3

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.9783. Min Act: -0.1700

Data Index: 1585571 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 4.0292. Min Range: -4.0292

Max Act: 4.0177. Min Act: -0.1700

Data Index: 7533782 (Open Web Text)

Max Activating Token Index: 710

Text #5

Max Range: 4.0292. Min Range: -4.0292

Max Act: 4.0137. Min Act: -0.1700

Data Index: 5428791 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.9593. Min Act: -0.1700

Data Index: 538872 (Open Web Text)

Max Activating Token Index: 272

Text #7

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.9748. Min Act: -0.1700

Data Index: 2250810 (Open Web Text)

Max Activating Token Index: 546

Text #8

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.9254. Min Act: -0.1700

Data Index: 6651109 (Open Web Text)

Max Activating Token Index: 506

Text #9

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.8680. Min Act: -0.1700

Data Index: 6334146 (Open Web Text)

Max Activating Token Index: 827

Text #10

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.9093. Min Act: -0.1700

Data Index: 5064938 (Open Web Text)

Max Activating Token Index: 992

Text #11

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.8960. Min Act: -0.1700

Data Index: 1988878 (Open Web Text)

Max Activating Token Index: 346

Text #12

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.8518. Min Act: -0.1700

Data Index: 3650177 (Open Web Text)

Max Activating Token Index: 746

Text #13

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.9223. Min Act: -0.1700

Data Index: 3994917 (Open Web Text)

Max Activating Token Index: 558

Text #14

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.8233. Min Act: -0.1700

Data Index: 7807091 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.8619. Min Act: -0.1700

Data Index: 8182141 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.8524. Min Act: -0.1700

Data Index: 604944 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.8444. Min Act: -0.1700

Data Index: 4283108 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.8505. Min Act: -0.1700

Data Index: 5763033 (Open Web Text)

Max Activating Token Index: 390

Text #19

Max Range: 4.0292. Min Range: -4.0292

Max Act: 3.8342. Min Act: -0.1700

Data Index: 6334152 (Open Web Text)

Max Activating Token Index: 110