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

Dataset: Open Web Text

Neuron 2057 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: 4.2339. Min Range: -4.2339

Max Act: 4.2113. Min Act: -0.1700

Data Index: 4405418 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.2339. Min Act: -0.1700

Data Index: 483619 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.1746. Min Act: -0.1700

Data Index: 5991303 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.2296. Min Act: -0.1700

Data Index: 4270428 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.1649. Min Act: -0.1700

Data Index: 4723141 (Open Web Text)

Max Activating Token Index: 520

Text #5

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.1604. Min Act: -0.1700

Data Index: 6703181 (Open Web Text)

Max Activating Token Index: 428

Text #6

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.1367. Min Act: -0.1700

Data Index: 4643329 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.1624. Min Act: -0.1700

Data Index: 3623798 (Open Web Text)

Max Activating Token Index: 351

Text #8

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.0880. Min Act: -0.1700

Data Index: 8128018 (Open Web Text)

Max Activating Token Index: 676

Text #9

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.1229. Min Act: -0.1700

Data Index: 1455065 (Open Web Text)

Max Activating Token Index: 352

Text #10

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.1102. Min Act: -0.1700

Data Index: 7845655 (Open Web Text)

Max Activating Token Index: 204

Text #11

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.1244. Min Act: -0.1700

Data Index: 7582283 (Open Web Text)

Max Activating Token Index: 898

Text #12

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.0865. Min Act: -0.1700

Data Index: 7386106 (Open Web Text)

Max Activating Token Index: 236

Text #13

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.0909. Min Act: -0.1700

Data Index: 7381586 (Open Web Text)

Max Activating Token Index: 985

Text #14

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.1078. Min Act: -0.1700

Data Index: 1258964 (Open Web Text)

Max Activating Token Index: 827

Text #15

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.0871. Min Act: -0.1700

Data Index: 5409977 (Open Web Text)

Max Activating Token Index: 388

Text #16

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.1140. Min Act: -0.1700

Data Index: 5386732 (Open Web Text)

Max Activating Token Index: 111

Text #17

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.0915. Min Act: -0.1700

Data Index: 5101423 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.0776. Min Act: -0.1700

Data Index: 3986689 (Open Web Text)

Max Activating Token Index: 533

Text #19

Max Range: 4.2339. Min Range: -4.2339

Max Act: 4.1190. Min Act: -0.1700

Data Index: 1524786 (Open Web Text)

Max Activating Token Index: 926