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

Dataset: Open Web Text

Neuron 2176 in Layer 1

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: 3.6007. Min Range: -3.6007

Max Act: 3.6007. Min Act: -0.1700

Data Index: 8759460 (Open Web Text)

Max Activating Token Index: 295

Text #1

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5435. Min Act: -0.1700

Data Index: 7781601 (Open Web Text)

Max Activating Token Index: 119

Text #2

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5208. Min Act: -0.1700

Data Index: 2363311 (Open Web Text)

Max Activating Token Index: 886

Text #3

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5113. Min Act: -0.1700

Data Index: 3359715 (Open Web Text)

Max Activating Token Index: 409

Text #4

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5122. Min Act: -0.1700

Data Index: 1245536 (Open Web Text)

Max Activating Token Index: 528

Text #5

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5375. Min Act: -0.1700

Data Index: 7328912 (Open Web Text)

Max Activating Token Index: 539

Text #6

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4981. Min Act: -0.1700

Data Index: 6325678 (Open Web Text)

Max Activating Token Index: 192

Text #7

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5350. Min Act: -0.1700

Data Index: 465694 (Open Web Text)

Max Activating Token Index: 426

Text #8

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5120. Min Act: -0.1700

Data Index: 6185385 (Open Web Text)

Max Activating Token Index: 514

Text #9

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5166. Min Act: -0.1700

Data Index: 2311604 (Open Web Text)

Max Activating Token Index: 955

Text #10

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4723. Min Act: -0.1700

Data Index: 5632705 (Open Web Text)

Max Activating Token Index: 523

Text #11

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4829. Min Act: -0.1700

Data Index: 6171865 (Open Web Text)

Max Activating Token Index: 787

Text #12

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4973. Min Act: -0.1700

Data Index: 7832284 (Open Web Text)

Max Activating Token Index: 632

Text #13

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4794. Min Act: -0.1700

Data Index: 8033441 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4726. Min Act: -0.1700

Data Index: 2660734 (Open Web Text)

Max Activating Token Index: 363

Text #15

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4804. Min Act: -0.1700

Data Index: 3149484 (Open Web Text)

Max Activating Token Index: 335

Text #16

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4840. Min Act: -0.1700

Data Index: 2161513 (Open Web Text)

Max Activating Token Index: 131

Text #17

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4836. Min Act: -0.1700

Data Index: 8094594 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4865. Min Act: -0.1700

Data Index: 8624263 (Open Web Text)

Max Activating Token Index: 608

Text #19

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4956. Min Act: -0.1700

Data Index: 5692120 (Open Web Text)

Max Activating Token Index: 337