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

Dataset: Open Web Text

Neuron 1487 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: 2.7656. Min Range: -2.7656

Max Act: 2.7656. Min Act: -0.1700

Data Index: 8755394 (Open Web Text)

Max Activating Token Index: 741

Text #1

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.7543. Min Act: -0.1700

Data Index: 7023097 (Open Web Text)

Max Activating Token Index: 252

Text #2

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.7555. Min Act: -0.1700

Data Index: 1968850 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.7550. Min Act: -0.1700

Data Index: 3900818 (Open Web Text)

Max Activating Token Index: 244

Text #4

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.7244. Min Act: -0.1700

Data Index: 7832843 (Open Web Text)

Max Activating Token Index: 77

Text #5

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.7331. Min Act: -0.1700

Data Index: 7826263 (Open Web Text)

Max Activating Token Index: 143

Text #6

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.7057. Min Act: -0.1700

Data Index: 6233455 (Open Web Text)

Max Activating Token Index: 303

Text #7

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6977. Min Act: -0.1700

Data Index: 2024432 (Open Web Text)

Max Activating Token Index: 467

Text #8

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6797. Min Act: -0.1700

Data Index: 4991613 (Open Web Text)

Max Activating Token Index: 77

Text #9

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6843. Min Act: -0.1700

Data Index: 6655763 (Open Web Text)

Max Activating Token Index: 969

Text #10

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6783. Min Act: -0.1700

Data Index: 2354944 (Open Web Text)

Max Activating Token Index: 345

Text #11

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6638. Min Act: -0.1700

Data Index: 4164631 (Open Web Text)

Max Activating Token Index: 172

Text #12

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6727. Min Act: -0.1700

Data Index: 5791166 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6693. Min Act: -0.1700

Data Index: 7688210 (Open Web Text)

Max Activating Token Index: 99

Text #14

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6377. Min Act: -0.1700

Data Index: 5931506 (Open Web Text)

Max Activating Token Index: 179

Text #15

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6417. Min Act: -0.1700

Data Index: 1377849 (Open Web Text)

Max Activating Token Index: 406

Text #16

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6537. Min Act: -0.1700

Data Index: 2235204 (Open Web Text)

Max Activating Token Index: 869

Text #17

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6479. Min Act: -0.1700

Data Index: 7343331 (Open Web Text)

Max Activating Token Index: 598

Text #18

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6493. Min Act: -0.1700

Data Index: 4577586 (Open Web Text)

Max Activating Token Index: 979

Text #19

Max Range: 2.7656. Min Range: -2.7656

Max Act: 2.6418. Min Act: -0.1700

Data Index: 7987311 (Open Web Text)

Max Activating Token Index: 511