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

Dataset: Open Web Text

Neuron 316 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: 3.7577. Min Range: -3.7577

Max Act: 3.7577. Min Act: -0.1700

Data Index: 306937 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.7576. Min Act: -0.1700

Data Index: 5382198 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.7200. Min Act: -0.1700

Data Index: 624446 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.7177. Min Act: -0.1700

Data Index: 4436326 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.7135. Min Act: -0.1700

Data Index: 1953509 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6990. Min Act: -0.1700

Data Index: 8561679 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6990. Min Act: -0.1700

Data Index: 3330950 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6990. Min Act: -0.1700

Data Index: 1212822 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6990. Min Act: -0.1700

Data Index: 1075123 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6990. Min Act: -0.1700

Data Index: 6927159 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6684. Min Act: -0.1700

Data Index: 6678741 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6778. Min Act: -0.1700

Data Index: 3951880 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6772. Min Act: -0.1700

Data Index: 1669463 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6990. Min Act: -0.1700

Data Index: 3504602 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6486. Min Act: -0.1700

Data Index: 899974 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6484. Min Act: -0.1700

Data Index: 6643302 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6527. Min Act: -0.1700

Data Index: 2426137 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6088. Min Act: -0.1700

Data Index: 6271212 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6286. Min Act: -0.1700

Data Index: 6273863 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.7577. Min Range: -3.7577

Max Act: 3.6260. Min Act: -0.1700

Data Index: 2223462 (Open Web Text)

Max Activating Token Index: 5