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

Dataset: Open Web Text

Neuron 243 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: 3.7518. Min Range: -3.7518

Max Act: 3.7518. Min Act: -0.1700

Data Index: 8562020 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.7281. Min Act: -0.1700

Data Index: 8166597 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.6938. Min Act: -0.1700

Data Index: 5205024 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.6337. Min Act: -0.1700

Data Index: 6799722 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.6014. Min Act: -0.1700

Data Index: 7464748 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.6069. Min Act: -0.1700

Data Index: 7074505 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.6108. Min Act: -0.1700

Data Index: 3013981 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.6187. Min Act: -0.1700

Data Index: 3742463 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.6008. Min Act: -0.1700

Data Index: 2770171 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.6182. Min Act: -0.1700

Data Index: 3213520 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.5790. Min Act: -0.1700

Data Index: 2458773 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.5801. Min Act: -0.1700

Data Index: 5193730 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.5693. Min Act: -0.1700

Data Index: 3311132 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.5774. Min Act: -0.1700

Data Index: 2303348 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.5713. Min Act: -0.1700

Data Index: 1107818 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.5803. Min Act: -0.1700

Data Index: 8318094 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.5723. Min Act: -0.1700

Data Index: 7694526 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.5686. Min Act: -0.1700

Data Index: 429290 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.5396. Min Act: -0.1700

Data Index: 3875767 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.5588. Min Act: -0.1700

Data Index: 462781 (Open Web Text)

Max Activating Token Index: 5