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

Dataset: Open Web Text

Neuron 1481 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: 4.1081. Min Range: -4.1081

Max Act: 4.1081. Min Act: -0.1700

Data Index: 5035981 (Open Web Text)

Max Activating Token Index: 1009

Text #1

Max Range: 4.1081. Min Range: -4.1081

Max Act: 4.0130. Min Act: -0.1700

Data Index: 6203051 (Open Web Text)

Max Activating Token Index: 340

Text #2

Max Range: 4.1081. Min Range: -4.1081

Max Act: 4.0299. Min Act: -0.1700

Data Index: 6869938 (Open Web Text)

Max Activating Token Index: 497

Text #3

Max Range: 4.1081. Min Range: -4.1081

Max Act: 4.0304. Min Act: -0.1700

Data Index: 7487012 (Open Web Text)

Max Activating Token Index: 569

Text #4

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9549. Min Act: -0.1700

Data Index: 2715388 (Open Web Text)

Max Activating Token Index: 528

Text #5

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9743. Min Act: -0.1700

Data Index: 568226 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 4.1081. Min Range: -4.1081

Max Act: 4.0118. Min Act: -0.1700

Data Index: 7654582 (Open Web Text)

Max Activating Token Index: 615

Text #7

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9634. Min Act: -0.1700

Data Index: 3631272 (Open Web Text)

Max Activating Token Index: 742

Text #8

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9685. Min Act: -0.1700

Data Index: 1446888 (Open Web Text)

Max Activating Token Index: 610

Text #9

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9584. Min Act: -0.1700

Data Index: 5510154 (Open Web Text)

Max Activating Token Index: 349

Text #10

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9085. Min Act: -0.1700

Data Index: 3463002 (Open Web Text)

Max Activating Token Index: 853

Text #11

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9367. Min Act: -0.1700

Data Index: 847541 (Open Web Text)

Max Activating Token Index: 624

Text #12

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9130. Min Act: -0.1700

Data Index: 954076 (Open Web Text)

Max Activating Token Index: 264

Text #13

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9617. Min Act: -0.1700

Data Index: 907750 (Open Web Text)

Max Activating Token Index: 411

Text #14

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9146. Min Act: -0.1700

Data Index: 7933206 (Open Web Text)

Max Activating Token Index: 195

Text #15

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8786. Min Act: -0.1700

Data Index: 1374956 (Open Web Text)

Max Activating Token Index: 739

Text #16

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9248. Min Act: -0.1700

Data Index: 2803348 (Open Web Text)

Max Activating Token Index: 744

Text #17

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8939. Min Act: -0.1700

Data Index: 5516472 (Open Web Text)

Max Activating Token Index: 150

Text #18

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9116. Min Act: -0.1700

Data Index: 5364617 (Open Web Text)

Max Activating Token Index: 807

Text #19

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8991. Min Act: -0.1700

Data Index: 1639826 (Open Web Text)

Max Activating Token Index: 746