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

Dataset: Open Web Text

Neuron 2761 in Layer 5

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: 5.6276. Min Range: -5.6276

Max Act: 5.6276. Min Act: -0.1700

Data Index: 4864070 (Open Web Text)

Max Activating Token Index: 947

Text #1

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.5905. Min Act: -0.1700

Data Index: 4781855 (Open Web Text)

Max Activating Token Index: 834

Text #2

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.3696. Min Act: -0.1700

Data Index: 8129368 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.3339. Min Act: -0.1700

Data Index: 466463 (Open Web Text)

Max Activating Token Index: 790

Text #4

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.4106. Min Act: -0.1700

Data Index: 6906638 (Open Web Text)

Max Activating Token Index: 493

Text #5

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.3154. Min Act: -0.1700

Data Index: 8678944 (Open Web Text)

Max Activating Token Index: 984

Text #6

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.1265. Min Act: -0.1700

Data Index: 5954149 (Open Web Text)

Max Activating Token Index: 713

Text #7

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.2892. Min Act: -0.1700

Data Index: 3102898 (Open Web Text)

Max Activating Token Index: 194

Text #8

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.1962. Min Act: -0.1700

Data Index: 7677230 (Open Web Text)

Max Activating Token Index: 572

Text #9

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.2582. Min Act: -0.1700

Data Index: 5496811 (Open Web Text)

Max Activating Token Index: 975

Text #10

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.2304. Min Act: -0.1700

Data Index: 489087 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.2005. Min Act: -0.1700

Data Index: 3955949 (Open Web Text)

Max Activating Token Index: 831

Text #12

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.1310. Min Act: -0.1700

Data Index: 6494108 (Open Web Text)

Max Activating Token Index: 864

Text #13

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.1353. Min Act: -0.1700

Data Index: 3220000 (Open Web Text)

Max Activating Token Index: 123

Text #14

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.1103. Min Act: -0.1700

Data Index: 2813300 (Open Web Text)

Max Activating Token Index: 830

Text #15

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.1066. Min Act: -0.1700

Data Index: 4460907 (Open Web Text)

Max Activating Token Index: 1009

Text #16

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.1524. Min Act: -0.1700

Data Index: 1269781 (Open Web Text)

Max Activating Token Index: 240

Text #17

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.1170. Min Act: -0.1700

Data Index: 8209174 (Open Web Text)

Max Activating Token Index: 790

Text #18

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.1290. Min Act: -0.1700

Data Index: 8361613 (Open Web Text)

Max Activating Token Index: 678

Text #19

Max Range: 5.6276. Min Range: -5.6276

Max Act: 5.0707. Min Act: -0.1700

Data Index: 2795621 (Open Web Text)

Max Activating Token Index: 599