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

Dataset: Open Web Text

Neuron 301 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: 2.2959. Min Range: -2.2959

Max Act: 2.2959. Min Act: -0.1700

Data Index: 7449446 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.2737. Min Act: -0.1700

Data Index: 2677472 (Open Web Text)

Max Activating Token Index: 59

Text #2

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.2140. Min Act: -0.1700

Data Index: 2114190 (Open Web Text)

Max Activating Token Index: 31

Text #3

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1903. Min Act: -0.1700

Data Index: 3686550 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.2077. Min Act: -0.1700

Data Index: 1483971 (Open Web Text)

Max Activating Token Index: 533

Text #5

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1808. Min Act: -0.1700

Data Index: 6057314 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1830. Min Act: -0.1700

Data Index: 187833 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1594. Min Act: -0.1700

Data Index: 4028110 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1651. Min Act: -0.1700

Data Index: 4794656 (Open Web Text)

Max Activating Token Index: 106

Text #9

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1637. Min Act: -0.1700

Data Index: 5147027 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1594. Min Act: -0.1700

Data Index: 5098861 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1633. Min Act: -0.1700

Data Index: 1754424 (Open Web Text)

Max Activating Token Index: 351

Text #12

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1525. Min Act: -0.1700

Data Index: 5233114 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1604. Min Act: -0.1700

Data Index: 4829570 (Open Web Text)

Max Activating Token Index: 59

Text #14

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1486. Min Act: -0.1700

Data Index: 3291734 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1441. Min Act: -0.1700

Data Index: 7483589 (Open Web Text)

Max Activating Token Index: 103

Text #16

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1486. Min Act: -0.1700

Data Index: 515076 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1556. Min Act: -0.1700

Data Index: 2527068 (Open Web Text)

Max Activating Token Index: 441

Text #18

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1272. Min Act: -0.1700

Data Index: 3312626 (Open Web Text)

Max Activating Token Index: 608

Text #19

Max Range: 2.2959. Min Range: -2.2959

Max Act: 2.1219. Min Act: -0.1700

Data Index: 733883 (Open Web Text)

Max Activating Token Index: 7