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

Dataset: Open Web Text

Neuron 1269 in Layer 6

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: 5.1712. Min Range: -5.1712

Max Act: 5.1712. Min Act: -0.1700

Data Index: 7476864 (Open Web Text)

Max Activating Token Index: 89

Text #1

Max Range: 5.1712. Min Range: -5.1712

Max Act: 5.0802. Min Act: -0.1700

Data Index: 8245016 (Open Web Text)

Max Activating Token Index: 895

Text #2

Max Range: 5.1712. Min Range: -5.1712

Max Act: 5.0286. Min Act: -0.1700

Data Index: 8156172 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.9984. Min Act: -0.1700

Data Index: 2043022 (Open Web Text)

Max Activating Token Index: 339

Text #4

Max Range: 5.1712. Min Range: -5.1712

Max Act: 5.0094. Min Act: -0.1700

Data Index: 692049 (Open Web Text)

Max Activating Token Index: 113

Text #5

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.9258. Min Act: -0.1700

Data Index: 1779817 (Open Web Text)

Max Activating Token Index: 194

Text #6

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.8579. Min Act: -0.1700

Data Index: 5846760 (Open Web Text)

Max Activating Token Index: 797

Text #7

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.8677. Min Act: -0.1700

Data Index: 368666 (Open Web Text)

Max Activating Token Index: 559

Text #8

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.7361. Min Act: -0.1700

Data Index: 1293321 (Open Web Text)

Max Activating Token Index: 598

Text #9

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.6725. Min Act: -0.1700

Data Index: 6295742 (Open Web Text)

Max Activating Token Index: 147

Text #10

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.6653. Min Act: -0.1700

Data Index: 4827127 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.5427. Min Act: -0.1700

Data Index: 5588736 (Open Web Text)

Max Activating Token Index: 947

Text #12

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.5431. Min Act: -0.1700

Data Index: 8669710 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.5251. Min Act: -0.1700

Data Index: 5653571 (Open Web Text)

Max Activating Token Index: 430

Text #14

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.5210. Min Act: -0.1700

Data Index: 2713691 (Open Web Text)

Max Activating Token Index: 927

Text #15

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.4943. Min Act: -0.1700

Data Index: 1881158 (Open Web Text)

Max Activating Token Index: 241

Text #16

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.5088. Min Act: -0.1700

Data Index: 110168 (Open Web Text)

Max Activating Token Index: 798

Text #17

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.4087. Min Act: -0.1700

Data Index: 3827795 (Open Web Text)

Max Activating Token Index: 717

Text #18

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.4659. Min Act: -0.1700

Data Index: 7024516 (Open Web Text)

Max Activating Token Index: 79

Text #19

Max Range: 5.1712. Min Range: -5.1712

Max Act: 4.4568. Min Act: -0.1700

Data Index: 8589323 (Open Web Text)

Max Activating Token Index: 33