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

Dataset: Open Web Text

Neuron 207 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: 3.9272. Min Range: -3.9272

Max Act: 3.9272. Min Act: -0.1700

Data Index: 7469630 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.9272. Min Act: -0.1700

Data Index: 8224411 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.9272. Min Act: -0.1700

Data Index: 2068337 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.9272. Min Act: -0.1700

Data Index: 3343631 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.9272. Min Act: -0.1700

Data Index: 8735437 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.9272. Min Act: -0.1700

Data Index: 5509967 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.9123. Min Act: -0.1700

Data Index: 6872239 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8814. Min Act: -0.1700

Data Index: 6845501 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8753. Min Act: -0.1700

Data Index: 1179068 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8621. Min Act: -0.1700

Data Index: 4929002 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8622. Min Act: -0.1700

Data Index: 6770815 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8303. Min Act: -0.1700

Data Index: 1509488 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8319. Min Act: -0.1700

Data Index: 6865744 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8432. Min Act: -0.1700

Data Index: 4961456 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8360. Min Act: -0.1700

Data Index: 7173243 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8369. Min Act: -0.1700

Data Index: 1039121 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8360. Min Act: -0.1700

Data Index: 2693774 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8250. Min Act: -0.1700

Data Index: 7320628 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8270. Min Act: -0.1700

Data Index: 3570721 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.9272. Min Range: -3.9272

Max Act: 3.8360. Min Act: -0.1700

Data Index: 3571877 (Open Web Text)

Max Activating Token Index: 2