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

Dataset: Open Web Text

Neuron 624 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: 3.9597. Min Range: -3.9597

Max Act: 3.9597. Min Act: -0.1700

Data Index: 2399926 (Open Web Text)

Max Activating Token Index: 999

Text #1

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9292. Min Act: -0.1700

Data Index: 2637612 (Open Web Text)

Max Activating Token Index: 996

Text #2

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9279. Min Act: -0.1700

Data Index: 4857562 (Open Web Text)

Max Activating Token Index: 718

Text #3

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9172. Min Act: -0.1700

Data Index: 3760499 (Open Web Text)

Max Activating Token Index: 600

Text #4

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9007. Min Act: -0.1700

Data Index: 8429534 (Open Web Text)

Max Activating Token Index: 199

Text #5

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9163. Min Act: -0.1700

Data Index: 7920893 (Open Web Text)

Max Activating Token Index: 668

Text #6

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8934. Min Act: -0.1700

Data Index: 690762 (Open Web Text)

Max Activating Token Index: 820

Text #7

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9148. Min Act: -0.1700

Data Index: 886128 (Open Web Text)

Max Activating Token Index: 546

Text #8

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9248. Min Act: -0.1700

Data Index: 2920604 (Open Web Text)

Max Activating Token Index: 175

Text #9

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9106. Min Act: -0.1700

Data Index: 1728600 (Open Web Text)

Max Activating Token Index: 995

Text #10

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8820. Min Act: -0.1700

Data Index: 874500 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9149. Min Act: -0.1700

Data Index: 1665276 (Open Web Text)

Max Activating Token Index: 378

Text #12

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9218. Min Act: -0.1700

Data Index: 6994794 (Open Web Text)

Max Activating Token Index: 164

Text #13

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9051. Min Act: -0.1700

Data Index: 2880070 (Open Web Text)

Max Activating Token Index: 994

Text #14

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8836. Min Act: -0.1700

Data Index: 4819828 (Open Web Text)

Max Activating Token Index: 796

Text #15

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9115. Min Act: -0.1700

Data Index: 3817175 (Open Web Text)

Max Activating Token Index: 190

Text #16

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9166. Min Act: -0.1700

Data Index: 3773378 (Open Web Text)

Max Activating Token Index: 745

Text #17

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8871. Min Act: -0.1700

Data Index: 1144239 (Open Web Text)

Max Activating Token Index: 396

Text #18

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8667. Min Act: -0.1700

Data Index: 3172694 (Open Web Text)

Max Activating Token Index: 259

Text #19

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8585. Min Act: -0.1700

Data Index: 1983204 (Open Web Text)

Max Activating Token Index: 465