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

Dataset: Open Web Text

Neuron 1022 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: 4.4174. Min Range: -4.4174

Max Act: 4.4174. Min Act: -0.1700

Data Index: 6144464 (Open Web Text)

Max Activating Token Index: 600

Text #1

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.3951. Min Act: -0.1700

Data Index: 2538261 (Open Web Text)

Max Activating Token Index: 446

Text #2

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.4058. Min Act: -0.1700

Data Index: 4762893 (Open Web Text)

Max Activating Token Index: 824

Text #3

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.3895. Min Act: -0.1700

Data Index: 6049842 (Open Web Text)

Max Activating Token Index: 334

Text #4

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.3468. Min Act: -0.1700

Data Index: 1777975 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.3287. Min Act: -0.1700

Data Index: 7818866 (Open Web Text)

Max Activating Token Index: 890

Text #6

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2973. Min Act: -0.1700

Data Index: 6278661 (Open Web Text)

Max Activating Token Index: 917

Text #7

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.3415. Min Act: -0.1700

Data Index: 539016 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.3425. Min Act: -0.1700

Data Index: 946922 (Open Web Text)

Max Activating Token Index: 811

Text #9

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.3206. Min Act: -0.1700

Data Index: 5829450 (Open Web Text)

Max Activating Token Index: 563

Text #10

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.3059. Min Act: -0.1700

Data Index: 6696058 (Open Web Text)

Max Activating Token Index: 835

Text #11

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2676. Min Act: -0.1700

Data Index: 1095634 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2403. Min Act: -0.1700

Data Index: 841410 (Open Web Text)

Max Activating Token Index: 809

Text #13

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2053. Min Act: -0.1700

Data Index: 3981458 (Open Web Text)

Max Activating Token Index: 873

Text #14

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2436. Min Act: -0.1700

Data Index: 6087285 (Open Web Text)

Max Activating Token Index: 364

Text #15

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2713. Min Act: -0.1700

Data Index: 5250783 (Open Web Text)

Max Activating Token Index: 512

Text #16

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2729. Min Act: -0.1700

Data Index: 5089199 (Open Web Text)

Max Activating Token Index: 211

Text #17

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2273. Min Act: -0.1700

Data Index: 3711549 (Open Web Text)

Max Activating Token Index: 130

Text #18

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2242. Min Act: -0.1700

Data Index: 5452533 (Open Web Text)

Max Activating Token Index: 167

Text #19

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2156. Min Act: -0.1700

Data Index: 6900257 (Open Web Text)

Max Activating Token Index: 213