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

Dataset: Open Web Text

Neuron 1868 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: 4.8605. Min Range: -4.8605

Max Act: 4.8605. Min Act: -0.1700

Data Index: 6257203 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.7313. Min Act: -0.1700

Data Index: 8738307 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.7310. Min Act: -0.1700

Data Index: 5491189 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6896. Min Act: -0.1700

Data Index: 4922894 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.7005. Min Act: -0.1700

Data Index: 6137406 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6990. Min Act: -0.1700

Data Index: 1510888 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.7058. Min Act: -0.1700

Data Index: 6949276 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6557. Min Act: -0.1700

Data Index: 7742073 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6633. Min Act: -0.1700

Data Index: 7976780 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6486. Min Act: -0.1700

Data Index: 2445455 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6737. Min Act: -0.1700

Data Index: 2570044 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6724. Min Act: -0.1700

Data Index: 4169436 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6220. Min Act: -0.1700

Data Index: 1998007 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6266. Min Act: -0.1700

Data Index: 2348322 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6279. Min Act: -0.1700

Data Index: 3880212 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6235. Min Act: -0.1700

Data Index: 8005250 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6276. Min Act: -0.1700

Data Index: 6698756 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6391. Min Act: -0.1700

Data Index: 942711 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6396. Min Act: -0.1700

Data Index: 1000766 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.8605. Min Range: -4.8605

Max Act: 4.6235. Min Act: -0.1700

Data Index: 3152749 (Open Web Text)

Max Activating Token Index: 3