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

Dataset: Open Web Text

Neuron 2800 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: 3.2224. Min Range: -3.2224

Max Act: 3.2224. Min Act: -0.1700

Data Index: 5431622 (Open Web Text)

Max Activating Token Index: 465

Text #1

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.1983. Min Act: -0.1700

Data Index: 1201819 (Open Web Text)

Max Activating Token Index: 587

Text #2

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.2003. Min Act: -0.1700

Data Index: 3263581 (Open Web Text)

Max Activating Token Index: 715

Text #3

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.1107. Min Act: -0.1700

Data Index: 5966016 (Open Web Text)

Max Activating Token Index: 173

Text #4

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.1415. Min Act: -0.1700

Data Index: 5966015 (Open Web Text)

Max Activating Token Index: 26

Text #5

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.1210. Min Act: -0.1700

Data Index: 6144525 (Open Web Text)

Max Activating Token Index: 742

Text #6

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0781. Min Act: -0.1700

Data Index: 7980097 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0686. Min Act: -0.1700

Data Index: 7980087 (Open Web Text)

Max Activating Token Index: 325

Text #8

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0787. Min Act: -0.1700

Data Index: 5562818 (Open Web Text)

Max Activating Token Index: 509

Text #9

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0868. Min Act: -0.1700

Data Index: 7980092 (Open Web Text)

Max Activating Token Index: 343

Text #10

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0774. Min Act: -0.1700

Data Index: 1851165 (Open Web Text)

Max Activating Token Index: 224

Text #11

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0501. Min Act: -0.1700

Data Index: 7980089 (Open Web Text)

Max Activating Token Index: 841

Text #12

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0317. Min Act: -0.1700

Data Index: 2789604 (Open Web Text)

Max Activating Token Index: 335

Text #13

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0373. Min Act: -0.1700

Data Index: 7980094 (Open Web Text)

Max Activating Token Index: 877

Text #14

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0066. Min Act: -0.1700

Data Index: 6302221 (Open Web Text)

Max Activating Token Index: 708

Text #15

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9845. Min Act: -0.1700

Data Index: 4394147 (Open Web Text)

Max Activating Token Index: 966

Text #16

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9753. Min Act: -0.1700

Data Index: 5522319 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9961. Min Act: -0.1700

Data Index: 6941125 (Open Web Text)

Max Activating Token Index: 202

Text #18

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9922. Min Act: -0.1700

Data Index: 5003290 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9979. Min Act: -0.1700

Data Index: 2580403 (Open Web Text)

Max Activating Token Index: 877