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

Dataset: Open Web Text

Neuron 1228 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: 4.6462. Min Range: -4.6462

Max Act: 4.6462. Min Act: -0.1700

Data Index: 4442771 (Open Web Text)

Max Activating Token Index: 883

Text #1

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.5095. Min Act: -0.1700

Data Index: 714296 (Open Web Text)

Max Activating Token Index: 254

Text #2

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.4748. Min Act: -0.1700

Data Index: 7135352 (Open Web Text)

Max Activating Token Index: 941

Text #3

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.4551. Min Act: -0.1700

Data Index: 5458257 (Open Web Text)

Max Activating Token Index: 730

Text #4

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.4803. Min Act: -0.1700

Data Index: 239049 (Open Web Text)

Max Activating Token Index: 458

Text #5

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.3559. Min Act: -0.1700

Data Index: 4510352 (Open Web Text)

Max Activating Token Index: 378

Text #6

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.3331. Min Act: -0.1700

Data Index: 5416954 (Open Web Text)

Max Activating Token Index: 793

Text #7

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.3319. Min Act: -0.1700

Data Index: 1581270 (Open Web Text)

Max Activating Token Index: 862

Text #8

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.3206. Min Act: -0.1700

Data Index: 1019494 (Open Web Text)

Max Activating Token Index: 344

Text #9

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.2969. Min Act: -0.1700

Data Index: 4198186 (Open Web Text)

Max Activating Token Index: 794

Text #10

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.2877. Min Act: -0.1700

Data Index: 7164244 (Open Web Text)

Max Activating Token Index: 398

Text #11

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.3318. Min Act: -0.1700

Data Index: 223041 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.3230. Min Act: -0.1700

Data Index: 657540 (Open Web Text)

Max Activating Token Index: 713

Text #13

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.3009. Min Act: -0.1700

Data Index: 6124774 (Open Web Text)

Max Activating Token Index: 183

Text #14

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.2942. Min Act: -0.1700

Data Index: 6071253 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.3351. Min Act: -0.1700

Data Index: 240907 (Open Web Text)

Max Activating Token Index: 266

Text #16

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.2558. Min Act: -0.1700

Data Index: 56510 (Open Web Text)

Max Activating Token Index: 490

Text #17

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.2736. Min Act: -0.1700

Data Index: 5418933 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.2966. Min Act: -0.1700

Data Index: 1010981 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 4.6462. Min Range: -4.6462

Max Act: 4.2640. Min Act: -0.1700

Data Index: 3739733 (Open Web Text)

Max Activating Token Index: 508