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

Dataset: Open Web Text

Neuron 2215 in Layer 1

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: 1.7145. Min Range: -1.7145

Max Act: 1.7145. Min Act: -0.1700

Data Index: 428747 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.6347. Min Act: -0.1700

Data Index: 6772757 (Open Web Text)

Max Activating Token Index: 584

Text #2

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.6293. Min Act: -0.1700

Data Index: 8489393 (Open Web Text)

Max Activating Token Index: 124

Text #3

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.6243. Min Act: -0.1700

Data Index: 4248405 (Open Web Text)

Max Activating Token Index: 604

Text #4

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.6099. Min Act: -0.1700

Data Index: 8371353 (Open Web Text)

Max Activating Token Index: 891

Text #5

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.6066. Min Act: -0.1700

Data Index: 4338662 (Open Web Text)

Max Activating Token Index: 818

Text #6

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.6118. Min Act: -0.1700

Data Index: 2464059 (Open Web Text)

Max Activating Token Index: 668

Text #7

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5923. Min Act: -0.1700

Data Index: 1183833 (Open Web Text)

Max Activating Token Index: 377

Text #8

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5861. Min Act: -0.1700

Data Index: 6936778 (Open Web Text)

Max Activating Token Index: 470

Text #9

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5991. Min Act: -0.1700

Data Index: 4233499 (Open Web Text)

Max Activating Token Index: 969

Text #10

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5856. Min Act: -0.1700

Data Index: 4193804 (Open Web Text)

Max Activating Token Index: 573

Text #11

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5938. Min Act: -0.1700

Data Index: 4251479 (Open Web Text)

Max Activating Token Index: 609

Text #12

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5934. Min Act: -0.1700

Data Index: 2631269 (Open Web Text)

Max Activating Token Index: 477

Text #13

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5878. Min Act: -0.1700

Data Index: 3859922 (Open Web Text)

Max Activating Token Index: 494

Text #14

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5814. Min Act: -0.1700

Data Index: 212593 (Open Web Text)

Max Activating Token Index: 964

Text #15

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5784. Min Act: -0.1700

Data Index: 555090 (Open Web Text)

Max Activating Token Index: 446

Text #16

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5882. Min Act: -0.1700

Data Index: 1529257 (Open Web Text)

Max Activating Token Index: 349

Text #17

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5762. Min Act: -0.1700

Data Index: 2977746 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5769. Min Act: -0.1700

Data Index: 6132785 (Open Web Text)

Max Activating Token Index: 257

Text #19

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.5777. Min Act: -0.1700

Data Index: 1165730 (Open Web Text)

Max Activating Token Index: 524