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

Dataset: Open Web Text

Neuron 413 in Layer 0

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: 3.2181. Min Range: -3.2181

Max Act: 3.2181. Min Act: -0.1700

Data Index: 7765887 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.2120. Min Act: -0.1700

Data Index: 6910808 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1958. Min Act: -0.1700

Data Index: 3550493 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1898. Min Act: -0.1700

Data Index: 7817950 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1978. Min Act: -0.1700

Data Index: 2385132 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1877. Min Act: -0.1700

Data Index: 4339995 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1793. Min Act: -0.1700

Data Index: 8604704 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1805. Min Act: -0.1700

Data Index: 8693599 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1522. Min Act: -0.1700

Data Index: 638549 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1425. Min Act: -0.1700

Data Index: 4098291 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1487. Min Act: -0.1700

Data Index: 7817952 (Open Web Text)

Max Activating Token Index: 33

Text #11

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1347. Min Act: -0.1700

Data Index: 5611351 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1385. Min Act: -0.1700

Data Index: 3158323 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1221. Min Act: -0.1700

Data Index: 1031826 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1233. Min Act: -0.1700

Data Index: 944768 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1175. Min Act: -0.1700

Data Index: 159738 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1099. Min Act: -0.1700

Data Index: 5476142 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1076. Min Act: -0.1700

Data Index: 4171511 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.0993. Min Act: -0.1700

Data Index: 1357317 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.0977. Min Act: -0.1700

Data Index: 5400377 (Open Web Text)

Max Activating Token Index: 4