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

Dataset: Open Web Text

Neuron 145 in Layer 5

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: 4.7784. Min Range: -4.7784

Max Act: 4.7784. Min Act: -0.1700

Data Index: 417402 (Open Web Text)

Max Activating Token Index: 478

Text #1

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.5907. Min Act: -0.1700

Data Index: 8236607 (Open Web Text)

Max Activating Token Index: 569

Text #2

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.5510. Min Act: -0.1700

Data Index: 7410395 (Open Web Text)

Max Activating Token Index: 518

Text #3

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.5384. Min Act: -0.1700

Data Index: 6801734 (Open Web Text)

Max Activating Token Index: 884

Text #4

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.5266. Min Act: -0.1700

Data Index: 522869 (Open Web Text)

Max Activating Token Index: 955

Text #5

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.5047. Min Act: -0.1700

Data Index: 5230746 (Open Web Text)

Max Activating Token Index: 381

Text #6

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4858. Min Act: -0.1700

Data Index: 581562 (Open Web Text)

Max Activating Token Index: 730

Text #7

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4756. Min Act: -0.1700

Data Index: 417397 (Open Web Text)

Max Activating Token Index: 33

Text #8

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4821. Min Act: -0.1700

Data Index: 3865485 (Open Web Text)

Max Activating Token Index: 268

Text #9

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4622. Min Act: -0.1700

Data Index: 4317812 (Open Web Text)

Max Activating Token Index: 570

Text #10

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4410. Min Act: -0.1700

Data Index: 151974 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4740. Min Act: -0.1700

Data Index: 1440499 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4734. Min Act: -0.1700

Data Index: 8179572 (Open Web Text)

Max Activating Token Index: 980

Text #13

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4564. Min Act: -0.1700

Data Index: 980736 (Open Web Text)

Max Activating Token Index: 490

Text #14

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4559. Min Act: -0.1700

Data Index: 5460779 (Open Web Text)

Max Activating Token Index: 915

Text #15

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4165. Min Act: -0.1700

Data Index: 8336547 (Open Web Text)

Max Activating Token Index: 667

Text #16

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4493. Min Act: -0.1700

Data Index: 1355598 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4181. Min Act: -0.1700

Data Index: 258830 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4285. Min Act: -0.1700

Data Index: 6406105 (Open Web Text)

Max Activating Token Index: 43

Text #19

Max Range: 4.7784. Min Range: -4.7784

Max Act: 4.4470. Min Act: -0.1700

Data Index: 6268836 (Open Web Text)

Max Activating Token Index: 926