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

Dataset: Open Web Text

Neuron 255 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: 4.3263. Min Range: -4.3263

Max Act: 4.3263. Min Act: -0.1700

Data Index: 200670 (Open Web Text)

Max Activating Token Index: 338

Text #1

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.2906. Min Act: -0.1700

Data Index: 4699613 (Open Web Text)

Max Activating Token Index: 688

Text #2

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.2034. Min Act: -0.1700

Data Index: 6375066 (Open Web Text)

Max Activating Token Index: 281

Text #3

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.2358. Min Act: -0.1700

Data Index: 3690326 (Open Web Text)

Max Activating Token Index: 164

Text #4

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.2375. Min Act: -0.1700

Data Index: 5823208 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.2084. Min Act: -0.1700

Data Index: 6226949 (Open Web Text)

Max Activating Token Index: 141

Text #6

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.2038. Min Act: -0.1700

Data Index: 6708664 (Open Web Text)

Max Activating Token Index: 39

Text #7

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1835. Min Act: -0.1700

Data Index: 773742 (Open Web Text)

Max Activating Token Index: 390

Text #8

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1696. Min Act: -0.1700

Data Index: 7823100 (Open Web Text)

Max Activating Token Index: 143

Text #9

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1879. Min Act: -0.1700

Data Index: 1692011 (Open Web Text)

Max Activating Token Index: 257

Text #10

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1728. Min Act: -0.1700

Data Index: 4048122 (Open Web Text)

Max Activating Token Index: 434

Text #11

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1900. Min Act: -0.1700

Data Index: 6366112 (Open Web Text)

Max Activating Token Index: 473

Text #12

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1634. Min Act: -0.1700

Data Index: 779251 (Open Web Text)

Max Activating Token Index: 204

Text #13

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1827. Min Act: -0.1700

Data Index: 3386591 (Open Web Text)

Max Activating Token Index: 809

Text #14

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1987. Min Act: -0.1700

Data Index: 2490034 (Open Web Text)

Max Activating Token Index: 846

Text #15

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1900. Min Act: -0.1700

Data Index: 2014005 (Open Web Text)

Max Activating Token Index: 607

Text #16

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1940. Min Act: -0.1700

Data Index: 268709 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1603. Min Act: -0.1700

Data Index: 2798512 (Open Web Text)

Max Activating Token Index: 339

Text #18

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.2084. Min Act: -0.1700

Data Index: 2679306 (Open Web Text)

Max Activating Token Index: 800

Text #19

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1395. Min Act: -0.1700

Data Index: 4156383 (Open Web Text)

Max Activating Token Index: 370