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

Dataset: Open Web Text

Neuron 2771 in Layer 6

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: 4.6572. Min Range: -4.6572

Max Act: 4.6572. Min Act: -0.1700

Data Index: 2252837 (Open Web Text)

Max Activating Token Index: 437

Text #1

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.6027. Min Act: -0.1700

Data Index: 5768292 (Open Web Text)

Max Activating Token Index: 937

Text #2

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.6295. Min Act: -0.1700

Data Index: 8489505 (Open Web Text)

Max Activating Token Index: 737

Text #3

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.6097. Min Act: -0.1700

Data Index: 6184777 (Open Web Text)

Max Activating Token Index: 375

Text #4

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.5972. Min Act: -0.1700

Data Index: 8466606 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.5592. Min Act: -0.1700

Data Index: 8795252 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.5787. Min Act: -0.1700

Data Index: 6961339 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.5503. Min Act: -0.1700

Data Index: 7908106 (Open Web Text)

Max Activating Token Index: 457

Text #8

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.5296. Min Act: -0.1700

Data Index: 8431224 (Open Web Text)

Max Activating Token Index: 434

Text #9

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.5828. Min Act: -0.1700

Data Index: 7355089 (Open Web Text)

Max Activating Token Index: 547

Text #10

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.5151. Min Act: -0.1700

Data Index: 615298 (Open Web Text)

Max Activating Token Index: 224

Text #11

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.4972. Min Act: -0.1700

Data Index: 7040435 (Open Web Text)

Max Activating Token Index: 93

Text #12

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.5107. Min Act: -0.1700

Data Index: 6969913 (Open Web Text)

Max Activating Token Index: 672

Text #13

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.4862. Min Act: -0.1700

Data Index: 2098979 (Open Web Text)

Max Activating Token Index: 358

Text #14

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.5087. Min Act: -0.1700

Data Index: 2329271 (Open Web Text)

Max Activating Token Index: 706

Text #15

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.4606. Min Act: -0.1700

Data Index: 4485544 (Open Web Text)

Max Activating Token Index: 506

Text #16

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.5000. Min Act: -0.1700

Data Index: 6129923 (Open Web Text)

Max Activating Token Index: 753

Text #17

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.4819. Min Act: -0.1700

Data Index: 7488934 (Open Web Text)

Max Activating Token Index: 515

Text #18

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.4540. Min Act: -0.1700

Data Index: 6034642 (Open Web Text)

Max Activating Token Index: 463

Text #19

Max Range: 4.6572. Min Range: -4.6572

Max Act: 4.4698. Min Act: -0.1700

Data Index: 8198092 (Open Web Text)

Max Activating Token Index: 743