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

Dataset: Open Web Text

Neuron 1053 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: 2.0023. Min Range: -2.0023

Max Act: 2.0023. Min Act: -0.1700

Data Index: 1103748 (Open Web Text)

Max Activating Token Index: 64

Text #1

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9857. Min Act: -0.1700

Data Index: 8795076 (Open Web Text)

Max Activating Token Index: 173

Text #2

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9640. Min Act: -0.1700

Data Index: 4687196 (Open Web Text)

Max Activating Token Index: 948

Text #3

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9771. Min Act: -0.1700

Data Index: 2133897 (Open Web Text)

Max Activating Token Index: 686

Text #4

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9576. Min Act: -0.1700

Data Index: 2396992 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9405. Min Act: -0.1700

Data Index: 3476441 (Open Web Text)

Max Activating Token Index: 115

Text #6

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9592. Min Act: -0.1700

Data Index: 2841228 (Open Web Text)

Max Activating Token Index: 116

Text #7

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9538. Min Act: -0.1700

Data Index: 693683 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9375. Min Act: -0.1700

Data Index: 8790324 (Open Web Text)

Max Activating Token Index: 970

Text #9

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9545. Min Act: -0.1700

Data Index: 5946175 (Open Web Text)

Max Activating Token Index: 491

Text #10

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9554. Min Act: -0.1700

Data Index: 1450906 (Open Web Text)

Max Activating Token Index: 519

Text #11

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9530. Min Act: -0.1700

Data Index: 8324431 (Open Web Text)

Max Activating Token Index: 498

Text #12

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9406. Min Act: -0.1700

Data Index: 1026412 (Open Web Text)

Max Activating Token Index: 1018

Text #13

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9294. Min Act: -0.1700

Data Index: 3227215 (Open Web Text)

Max Activating Token Index: 281

Text #14

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9360. Min Act: -0.1700

Data Index: 2978572 (Open Web Text)

Max Activating Token Index: 748

Text #15

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9344. Min Act: -0.1700

Data Index: 483883 (Open Web Text)

Max Activating Token Index: 332

Text #16

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9324. Min Act: -0.1700

Data Index: 6334249 (Open Web Text)

Max Activating Token Index: 702

Text #17

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9291. Min Act: -0.1700

Data Index: 2312162 (Open Web Text)

Max Activating Token Index: 180

Text #18

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9409. Min Act: -0.1700

Data Index: 6134126 (Open Web Text)

Max Activating Token Index: 341

Text #19

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.9296. Min Act: -0.1700

Data Index: 7201422 (Open Web Text)

Max Activating Token Index: 625