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

Dataset: Open Web Text

Neuron 671 in Layer 2

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: 4.5197. Min Range: -4.5197

Max Act: 4.5173. Min Act: -0.1700

Data Index: 899569 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.5197. Min Act: -0.1700

Data Index: 2093878 (Open Web Text)

Max Activating Token Index: 138

Text #2

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.4471. Min Act: -0.1700

Data Index: 3752698 (Open Web Text)

Max Activating Token Index: 28

Text #3

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.4770. Min Act: -0.1700

Data Index: 8472515 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.4576. Min Act: -0.1700

Data Index: 5921614 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.4422. Min Act: -0.1700

Data Index: 5798327 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.4448. Min Act: -0.1700

Data Index: 1821037 (Open Web Text)

Max Activating Token Index: 106

Text #7

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.4361. Min Act: -0.1700

Data Index: 2171708 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.4206. Min Act: -0.1700

Data Index: 4377305 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.4022. Min Act: -0.1700

Data Index: 1172125 (Open Web Text)

Max Activating Token Index: 163

Text #10

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.4107. Min Act: -0.1700

Data Index: 5698509 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.3640. Min Act: -0.1700

Data Index: 7523352 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.3680. Min Act: -0.1700

Data Index: 3270671 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.3590. Min Act: -0.1700

Data Index: 7779088 (Open Web Text)

Max Activating Token Index: 857

Text #14

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.3357. Min Act: -0.1700

Data Index: 3883275 (Open Web Text)

Max Activating Token Index: 862

Text #15

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.3272. Min Act: -0.1700

Data Index: 797788 (Open Web Text)

Max Activating Token Index: 194

Text #16

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.3569. Min Act: -0.1699

Data Index: 6724160 (Open Web Text)

Max Activating Token Index: 790

Text #17

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.3313. Min Act: -0.1700

Data Index: 850673 (Open Web Text)

Max Activating Token Index: 222

Text #18

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.3305. Min Act: -0.1700

Data Index: 4552714 (Open Web Text)

Max Activating Token Index: 981

Text #19

Max Range: 4.5197. Min Range: -4.5197

Max Act: 4.3238. Min Act: -0.1700

Data Index: 6619472 (Open Web Text)

Max Activating Token Index: 170