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

Dataset: Open Web Text

Neuron 1813 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: 3.9727. Min Range: -3.9727

Max Act: 3.9727. Min Act: -0.1700

Data Index: 4937947 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.8956. Min Act: -0.1700

Data Index: 3100508 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.8830. Min Act: -0.1700

Data Index: 169134 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.8830. Min Act: -0.1700

Data Index: 2508238 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.8830. Min Act: -0.1700

Data Index: 3487978 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.8830. Min Act: -0.1700

Data Index: 2364989 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.8830. Min Act: -0.1700

Data Index: 7877672 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.8968. Min Act: -0.1700

Data Index: 2456411 (Open Web Text)

Max Activating Token Index: 641

Text #8

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.8613. Min Act: -0.1700

Data Index: 2778549 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.8440. Min Act: -0.1700

Data Index: 2728280 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.8186. Min Act: -0.1700

Data Index: 2300723 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.8318. Min Act: -0.1700

Data Index: 5314833 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.7710. Min Act: -0.1700

Data Index: 5213007 (Open Web Text)

Max Activating Token Index: 358

Text #13

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.7639. Min Act: -0.1700

Data Index: 3628594 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.7834. Min Act: -0.1700

Data Index: 297307 (Open Web Text)

Max Activating Token Index: 81

Text #15

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.7639. Min Act: -0.1700

Data Index: 5015638 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.7639. Min Act: -0.1700

Data Index: 5141190 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.7639. Min Act: -0.1700

Data Index: 4663199 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.7855. Min Act: -0.1700

Data Index: 1732836 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.9727. Min Range: -3.9727

Max Act: 3.7980. Min Act: -0.1700

Data Index: 258679 (Open Web Text)

Max Activating Token Index: 18