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

Dataset: Open Web Text

Neuron 3042 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: 3.7364. Min Range: -3.7364

Max Act: 3.7364. Min Act: -0.1700

Data Index: 7360869 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6908. Min Act: -0.1700

Data Index: 4479157 (Open Web Text)

Max Activating Token Index: 913

Text #2

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6393. Min Act: -0.1700

Data Index: 3575910 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6450. Min Act: -0.1700

Data Index: 1632833 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6329. Min Act: -0.1700

Data Index: 1530035 (Open Web Text)

Max Activating Token Index: 972

Text #5

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6115. Min Act: -0.1700

Data Index: 3550007 (Open Web Text)

Max Activating Token Index: 260

Text #6

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6257. Min Act: -0.1700

Data Index: 2992511 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5789. Min Act: -0.1700

Data Index: 8241908 (Open Web Text)

Max Activating Token Index: 489

Text #8

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5701. Min Act: -0.1700

Data Index: 1543921 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5341. Min Act: -0.1700

Data Index: 5203284 (Open Web Text)

Max Activating Token Index: 806

Text #10

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5400. Min Act: -0.1700

Data Index: 2122556 (Open Web Text)

Max Activating Token Index: 749

Text #11

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5600. Min Act: -0.1700

Data Index: 5971759 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.4997. Min Act: -0.1700

Data Index: 4520723 (Open Web Text)

Max Activating Token Index: 258

Text #13

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5221. Min Act: -0.1700

Data Index: 7529940 (Open Web Text)

Max Activating Token Index: 151

Text #14

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.4824. Min Act: -0.1700

Data Index: 3055729 (Open Web Text)

Max Activating Token Index: 963

Text #15

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5393. Min Act: -0.1700

Data Index: 977167 (Open Web Text)

Max Activating Token Index: 252

Text #16

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.4826. Min Act: -0.1700

Data Index: 5453704 (Open Web Text)

Max Activating Token Index: 380

Text #17

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.4838. Min Act: -0.1700

Data Index: 5541067 (Open Web Text)

Max Activating Token Index: 341

Text #18

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5080. Min Act: -0.1700

Data Index: 4283126 (Open Web Text)

Max Activating Token Index: 265

Text #19

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.4963. Min Act: -0.1700

Data Index: 7509 (Open Web Text)

Max Activating Token Index: 382