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

Dataset: Open Web Text

Neuron 130 in Layer 2

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: 1.7466. Min Range: -1.7466

Max Act: 1.7466. Min Act: -0.1700

Data Index: 4865695 (Open Web Text)

Max Activating Token Index: 1003

Text #1

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.6275. Min Act: -0.1700

Data Index: 6612127 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.6130. Min Act: -0.1700

Data Index: 6833986 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.6114. Min Act: -0.1700

Data Index: 2273166 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5950. Min Act: -0.1700

Data Index: 1208338 (Open Web Text)

Max Activating Token Index: 44

Text #5

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5775. Min Act: -0.1700

Data Index: 7426076 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5797. Min Act: -0.1700

Data Index: 1815225 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5653. Min Act: -0.1700

Data Index: 1841522 (Open Web Text)

Max Activating Token Index: 428

Text #8

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5603. Min Act: -0.1622

Data Index: 7955193 (Open Web Text)

Max Activating Token Index: 484

Text #9

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5636. Min Act: -0.1700

Data Index: 2490098 (Open Web Text)

Max Activating Token Index: 448

Text #10

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5637. Min Act: -0.1700

Data Index: 6684592 (Open Web Text)

Max Activating Token Index: 912

Text #11

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5558. Min Act: -0.1700

Data Index: 2089128 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5469. Min Act: -0.1700

Data Index: 4214315 (Open Web Text)

Max Activating Token Index: 308

Text #13

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5527. Min Act: -0.1700

Data Index: 1656181 (Open Web Text)

Max Activating Token Index: 560

Text #14

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5405. Min Act: -0.1700

Data Index: 2264228 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5405. Min Act: -0.1700

Data Index: 3066900 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5405. Min Act: -0.1700

Data Index: 2732320 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5405. Min Act: -0.1700

Data Index: 1083719 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5405. Min Act: -0.1700

Data Index: 1564375 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.5387. Min Act: -0.1700

Data Index: 6878321 (Open Web Text)

Max Activating Token Index: 464