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

Dataset: Open Web Text

Neuron 115 in Layer 3

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: 4.3539. Min Range: -4.3539

Max Act: 4.3539. Min Act: -0.1700

Data Index: 5249629 (Open Web Text)

Max Activating Token Index: 445

Text #1

Max Range: 4.3539. Min Range: -4.3539

Max Act: 4.1972. Min Act: -0.1700

Data Index: 7186813 (Open Web Text)

Max Activating Token Index: 916

Text #2

Max Range: 4.3539. Min Range: -4.3539

Max Act: 4.0531. Min Act: -0.1700

Data Index: 4810568 (Open Web Text)

Max Activating Token Index: 388

Text #3

Max Range: 4.3539. Min Range: -4.3539

Max Act: 4.0537. Min Act: -0.1700

Data Index: 6807390 (Open Web Text)

Max Activating Token Index: 986

Text #4

Max Range: 4.3539. Min Range: -4.3539

Max Act: 4.0283. Min Act: -0.1700

Data Index: 1465637 (Open Web Text)

Max Activating Token Index: 229

Text #5

Max Range: 4.3539. Min Range: -4.3539

Max Act: 4.0160. Min Act: -0.1700

Data Index: 731589 (Open Web Text)

Max Activating Token Index: 488

Text #6

Max Range: 4.3539. Min Range: -4.3539

Max Act: 4.0091. Min Act: -0.1700

Data Index: 3977553 (Open Web Text)

Max Activating Token Index: 189

Text #7

Max Range: 4.3539. Min Range: -4.3539

Max Act: 4.0651. Min Act: -0.1700

Data Index: 8346724 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.3539. Min Range: -4.3539

Max Act: 4.0444. Min Act: -0.1700

Data Index: 5196426 (Open Web Text)

Max Activating Token Index: 876

Text #9

Max Range: 4.3539. Min Range: -4.3539

Max Act: 3.9665. Min Act: -0.1700

Data Index: 5970752 (Open Web Text)

Max Activating Token Index: 153

Text #10

Max Range: 4.3539. Min Range: -4.3539

Max Act: 3.9774. Min Act: -0.1700

Data Index: 3911221 (Open Web Text)

Max Activating Token Index: 716

Text #11

Max Range: 4.3539. Min Range: -4.3539

Max Act: 3.9867. Min Act: -0.1700

Data Index: 2420636 (Open Web Text)

Max Activating Token Index: 278

Text #12

Max Range: 4.3539. Min Range: -4.3539

Max Act: 3.9643. Min Act: -0.1700

Data Index: 3900445 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.3539. Min Range: -4.3539

Max Act: 3.9703. Min Act: -0.1700

Data Index: 4923775 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 4.3539. Min Range: -4.3539

Max Act: 4.0166. Min Act: -0.1700

Data Index: 5532854 (Open Web Text)

Max Activating Token Index: 591

Text #15

Max Range: 4.3539. Min Range: -4.3539

Max Act: 3.9696. Min Act: -0.1700

Data Index: 5970746 (Open Web Text)

Max Activating Token Index: 533

Text #16

Max Range: 4.3539. Min Range: -4.3539

Max Act: 3.9021. Min Act: -0.1700

Data Index: 4363510 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.3539. Min Range: -4.3539

Max Act: 3.9649. Min Act: -0.1700

Data Index: 3535320 (Open Web Text)

Max Activating Token Index: 386

Text #18

Max Range: 4.3539. Min Range: -4.3539

Max Act: 3.8910. Min Act: -0.1700

Data Index: 3594356 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 4.3539. Min Range: -4.3539

Max Act: 4.0185. Min Act: -0.1700

Data Index: 7440989 (Open Web Text)

Max Activating Token Index: 623