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

Dataset: Open Web Text

Neuron 891 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: 3.9863. Min Range: -3.9863

Max Act: 3.9863. Min Act: -0.1700

Data Index: 7007078 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.9626. Min Act: -0.1700

Data Index: 876418 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.9533. Min Act: -0.1700

Data Index: 2837855 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.9261. Min Act: -0.1700

Data Index: 317465 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8913. Min Act: -0.1700

Data Index: 4759336 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8791. Min Act: -0.1700

Data Index: 3124453 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8768. Min Act: -0.1700

Data Index: 8578792 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8666. Min Act: -0.1700

Data Index: 836517 (Open Web Text)

Max Activating Token Index: 540

Text #8

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8413. Min Act: -0.1700

Data Index: 2866015 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8511. Min Act: -0.1700

Data Index: 4367639 (Open Web Text)

Max Activating Token Index: 252

Text #10

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8535. Min Act: -0.1700

Data Index: 4332979 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8491. Min Act: -0.1700

Data Index: 213831 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8535. Min Act: -0.1700

Data Index: 5986267 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8503. Min Act: -0.1700

Data Index: 6855957 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8408. Min Act: -0.1700

Data Index: 1403776 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8416. Min Act: -0.1700

Data Index: 3171397 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8409. Min Act: -0.1700

Data Index: 2621944 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8324. Min Act: -0.1700

Data Index: 4894263 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7998. Min Act: -0.1700

Data Index: 2962304 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8206. Min Act: -0.1700

Data Index: 3836026 (Open Web Text)

Max Activating Token Index: 10