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

Dataset: Open Web Text

Neuron 957 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: 4.3166. Min Range: -4.3166

Max Act: 4.3166. Min Act: -0.1700

Data Index: 3006339 (Open Web Text)

Max Activating Token Index: 613

Text #1

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.2924. Min Act: -0.1700

Data Index: 2393389 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.2234. Min Act: -0.1700

Data Index: 5758022 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.2008. Min Act: -0.1700

Data Index: 3549761 (Open Web Text)

Max Activating Token Index: 940

Text #4

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1847. Min Act: -0.1700

Data Index: 450198 (Open Web Text)

Max Activating Token Index: 470

Text #5

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1909. Min Act: -0.1700

Data Index: 6836222 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.2390. Min Act: -0.1700

Data Index: 2778336 (Open Web Text)

Max Activating Token Index: 763

Text #7

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1623. Min Act: -0.1700

Data Index: 5318744 (Open Web Text)

Max Activating Token Index: 428

Text #8

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1760. Min Act: -0.1700

Data Index: 5416492 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1730. Min Act: -0.1700

Data Index: 4199529 (Open Web Text)

Max Activating Token Index: 72

Text #10

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1387. Min Act: -0.1700

Data Index: 8192928 (Open Web Text)

Max Activating Token Index: 61

Text #11

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1261. Min Act: -0.1700

Data Index: 7422638 (Open Web Text)

Max Activating Token Index: 320

Text #12

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1703. Min Act: -0.1700

Data Index: 2747056 (Open Web Text)

Max Activating Token Index: 31

Text #13

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1222. Min Act: -0.1700

Data Index: 7079890 (Open Web Text)

Max Activating Token Index: 721

Text #14

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1256. Min Act: -0.1700

Data Index: 465783 (Open Web Text)

Max Activating Token Index: 46

Text #15

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1458. Min Act: -0.1700

Data Index: 8495760 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1266. Min Act: -0.1700

Data Index: 1820276 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1683. Min Act: -0.1700

Data Index: 8800265 (Open Web Text)

Max Activating Token Index: 91

Text #18

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1267. Min Act: -0.1700

Data Index: 6677874 (Open Web Text)

Max Activating Token Index: 547

Text #19

Max Range: 4.3166. Min Range: -4.3166

Max Act: 4.1133. Min Act: -0.1700

Data Index: 745602 (Open Web Text)

Max Activating Token Index: 799