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

Dataset: Open Web Text

Neuron 2873 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: 4.3986. Min Range: -4.3986

Max Act: 4.3986. Min Act: -0.1700

Data Index: 2525305 (Open Web Text)

Max Activating Token Index: 998

Text #1

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.3859. Min Act: -0.1700

Data Index: 6463799 (Open Web Text)

Max Activating Token Index: 364

Text #2

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.2953. Min Act: -0.1700

Data Index: 2757879 (Open Web Text)

Max Activating Token Index: 618

Text #3

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.2787. Min Act: -0.1700

Data Index: 1129710 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.2774. Min Act: -0.1700

Data Index: 5909098 (Open Web Text)

Max Activating Token Index: 905

Text #5

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.2534. Min Act: -0.1700

Data Index: 2725500 (Open Web Text)

Max Activating Token Index: 104

Text #6

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.3455. Min Act: -0.1700

Data Index: 106657 (Open Web Text)

Max Activating Token Index: 827

Text #7

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.2919. Min Act: -0.1700

Data Index: 3044403 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.1445. Min Act: -0.1700

Data Index: 2280205 (Open Web Text)

Max Activating Token Index: 775

Text #9

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.1717. Min Act: -0.1700

Data Index: 6777194 (Open Web Text)

Max Activating Token Index: 869

Text #10

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.1570. Min Act: -0.1700

Data Index: 5157577 (Open Web Text)

Max Activating Token Index: 866

Text #11

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.1519. Min Act: -0.1700

Data Index: 1958464 (Open Web Text)

Max Activating Token Index: 634

Text #12

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.1429. Min Act: -0.1700

Data Index: 3062050 (Open Web Text)

Max Activating Token Index: 394

Text #13

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.0892. Min Act: -0.1700

Data Index: 5247439 (Open Web Text)

Max Activating Token Index: 730

Text #14

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.0974. Min Act: -0.1700

Data Index: 7012023 (Open Web Text)

Max Activating Token Index: 337

Text #15

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.0958. Min Act: -0.1700

Data Index: 3796408 (Open Web Text)

Max Activating Token Index: 297

Text #16

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.0360. Min Act: -0.1700

Data Index: 1123421 (Open Web Text)

Max Activating Token Index: 455

Text #17

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.0714. Min Act: -0.1700

Data Index: 1129708 (Open Web Text)

Max Activating Token Index: 895

Text #18

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.0909. Min Act: -0.1700

Data Index: 438324 (Open Web Text)

Max Activating Token Index: 59

Text #19

Max Range: 4.3986. Min Range: -4.3986

Max Act: 4.0454. Min Act: -0.1700

Data Index: 258237 (Open Web Text)

Max Activating Token Index: 17