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

Dataset: Open Web Text

Neuron 1830 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: 3.1711. Min Range: -3.1711

Max Act: 3.1711. Min Act: -0.1700

Data Index: 5697539 (Open Web Text)

Max Activating Token Index: 454

Text #1

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1542. Min Act: -0.1700

Data Index: 5169708 (Open Web Text)

Max Activating Token Index: 370

Text #2

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1038. Min Act: -0.1700

Data Index: 5413790 (Open Web Text)

Max Activating Token Index: 369

Text #3

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1098. Min Act: -0.1700

Data Index: 6570135 (Open Web Text)

Max Activating Token Index: 490

Text #4

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1266. Min Act: -0.1700

Data Index: 5861198 (Open Web Text)

Max Activating Token Index: 962

Text #5

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0784. Min Act: -0.1700

Data Index: 4171394 (Open Web Text)

Max Activating Token Index: 658

Text #6

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0681. Min Act: -0.1700

Data Index: 2122188 (Open Web Text)

Max Activating Token Index: 960

Text #7

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0670. Min Act: -0.1700

Data Index: 3492033 (Open Web Text)

Max Activating Token Index: 357

Text #8

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0642. Min Act: -0.1700

Data Index: 2623614 (Open Web Text)

Max Activating Token Index: 397

Text #9

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0453. Min Act: -0.1700

Data Index: 3910338 (Open Web Text)

Max Activating Token Index: 946

Text #10

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0213. Min Act: -0.1700

Data Index: 6137928 (Open Web Text)

Max Activating Token Index: 579

Text #11

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0152. Min Act: -0.1700

Data Index: 6575547 (Open Web Text)

Max Activating Token Index: 773

Text #12

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0016. Min Act: -0.1700

Data Index: 7395111 (Open Web Text)

Max Activating Token Index: 599

Text #13

Max Range: 3.1711. Min Range: -3.1711

Max Act: 2.9993. Min Act: -0.1700

Data Index: 7661648 (Open Web Text)

Max Activating Token Index: 894

Text #14

Max Range: 3.1711. Min Range: -3.1711

Max Act: 2.9892. Min Act: -0.1700

Data Index: 2399360 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 3.1711. Min Range: -3.1711

Max Act: 2.9831. Min Act: -0.1700

Data Index: 2641624 (Open Web Text)

Max Activating Token Index: 255

Text #16

Max Range: 3.1711. Min Range: -3.1711

Max Act: 2.9973. Min Act: -0.1700

Data Index: 2954010 (Open Web Text)

Max Activating Token Index: 547

Text #17

Max Range: 3.1711. Min Range: -3.1711

Max Act: 2.9771. Min Act: -0.1700

Data Index: 3132614 (Open Web Text)

Max Activating Token Index: 877

Text #18

Max Range: 3.1711. Min Range: -3.1711

Max Act: 2.9729. Min Act: -0.1700

Data Index: 3023924 (Open Web Text)

Max Activating Token Index: 705

Text #19

Max Range: 3.1711. Min Range: -3.1711

Max Act: 2.9891. Min Act: -0.1700

Data Index: 5152876 (Open Web Text)

Max Activating Token Index: 891