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

Dataset: Open Web Text

Neuron 2959 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: 2.2977. Min Range: -2.2977

Max Act: 2.2977. Min Act: -0.1700

Data Index: 6108776 (Open Web Text)

Max Activating Token Index: 472

Text #1

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.1921. Min Act: -0.1700

Data Index: 3964982 (Open Web Text)

Max Activating Token Index: 420

Text #2

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.1426. Min Act: -0.1700

Data Index: 3624707 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.1174. Min Act: -0.1700

Data Index: 3272064 (Open Web Text)

Max Activating Token Index: 443

Text #4

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0950. Min Act: -0.1700

Data Index: 5339219 (Open Web Text)

Max Activating Token Index: 417

Text #5

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.1147. Min Act: -0.1700

Data Index: 8207117 (Open Web Text)

Max Activating Token Index: 455

Text #6

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0958. Min Act: -0.1700

Data Index: 3107223 (Open Web Text)

Max Activating Token Index: 465

Text #7

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.1111. Min Act: -0.1700

Data Index: 3549021 (Open Web Text)

Max Activating Token Index: 434

Text #8

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0819. Min Act: -0.1700

Data Index: 2082934 (Open Web Text)

Max Activating Token Index: 451

Text #9

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0655. Min Act: -0.1700

Data Index: 4633099 (Open Web Text)

Max Activating Token Index: 418

Text #10

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0641. Min Act: -0.1700

Data Index: 2013127 (Open Web Text)

Max Activating Token Index: 386

Text #11

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0651. Min Act: -0.1700

Data Index: 590568 (Open Web Text)

Max Activating Token Index: 476

Text #12

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0580. Min Act: -0.1700

Data Index: 6566161 (Open Web Text)

Max Activating Token Index: 413

Text #13

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0268. Min Act: -0.1700

Data Index: 3523749 (Open Web Text)

Max Activating Token Index: 364

Text #14

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0416. Min Act: -0.1700

Data Index: 5009023 (Open Web Text)

Max Activating Token Index: 468

Text #15

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0436. Min Act: -0.1700

Data Index: 960755 (Open Web Text)

Max Activating Token Index: 428

Text #16

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0374. Min Act: -0.1700

Data Index: 3327348 (Open Web Text)

Max Activating Token Index: 428

Text #17

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0337. Min Act: -0.1700

Data Index: 5792755 (Open Web Text)

Max Activating Token Index: 371

Text #18

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0077. Min Act: -0.1700

Data Index: 2840491 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 2.2977. Min Range: -2.2977

Max Act: 2.0482. Min Act: -0.1700

Data Index: 1388888 (Open Web Text)

Max Activating Token Index: 420