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

Dataset: Open Web Text

Neuron 2806 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: 1.7957. Min Range: -1.7957

Max Act: 1.7957. Min Act: -0.1700

Data Index: 6665650 (Open Web Text)

Max Activating Token Index: 256

Text #1

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.7630. Min Act: -0.1700

Data Index: 7018266 (Open Web Text)

Max Activating Token Index: 53

Text #2

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.7577. Min Act: -0.1700

Data Index: 6135485 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.7329. Min Act: -0.1700

Data Index: 1016245 (Open Web Text)

Max Activating Token Index: 25

Text #4

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.7365. Min Act: -0.1700

Data Index: 8632393 (Open Web Text)

Max Activating Token Index: 171

Text #5

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.7072. Min Act: -0.1700

Data Index: 1026711 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6894. Min Act: -0.1700

Data Index: 6883758 (Open Web Text)

Max Activating Token Index: 232

Text #7

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6811. Min Act: -0.1700

Data Index: 1336346 (Open Web Text)

Max Activating Token Index: 343

Text #8

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6913. Min Act: -0.1700

Data Index: 1411481 (Open Web Text)

Max Activating Token Index: 279

Text #9

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6798. Min Act: -0.1700

Data Index: 913829 (Open Web Text)

Max Activating Token Index: 273

Text #10

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6757. Min Act: -0.1700

Data Index: 5335276 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6646. Min Act: -0.1700

Data Index: 6786945 (Open Web Text)

Max Activating Token Index: 837

Text #12

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6704. Min Act: -0.1700

Data Index: 4565121 (Open Web Text)

Max Activating Token Index: 238

Text #13

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6596. Min Act: -0.1700

Data Index: 683923 (Open Web Text)

Max Activating Token Index: 634

Text #14

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6554. Min Act: -0.1700

Data Index: 6301135 (Open Web Text)

Max Activating Token Index: 82

Text #15

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6657. Min Act: -0.1700

Data Index: 5434190 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6573. Min Act: -0.1700

Data Index: 4424117 (Open Web Text)

Max Activating Token Index: 134

Text #17

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6486. Min Act: -0.1699

Data Index: 7914522 (Open Web Text)

Max Activating Token Index: 422

Text #18

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6494. Min Act: -0.1700

Data Index: 2701894 (Open Web Text)

Max Activating Token Index: 322

Text #19

Max Range: 1.7957. Min Range: -1.7957

Max Act: 1.6601. Min Act: -0.1700

Data Index: 5287373 (Open Web Text)

Max Activating Token Index: 698