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

Dataset: Open Web Text

Neuron 1865 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: 2.5327. Min Range: -2.5327

Max Act: 2.5327. Min Act: -0.1700

Data Index: 3719161 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.4823. Min Act: -0.1700

Data Index: 7401105 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.3914. Min Act: -0.1700

Data Index: 2436738 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.3713. Min Act: -0.1700

Data Index: 5747435 (Open Web Text)

Max Activating Token Index: 30

Text #4

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.3650. Min Act: -0.1700

Data Index: 3554508 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.3437. Min Act: -0.1700

Data Index: 4318268 (Open Web Text)

Max Activating Token Index: 34

Text #6

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.3570. Min Act: -0.1700

Data Index: 7037869 (Open Web Text)

Max Activating Token Index: 23

Text #7

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.3336. Min Act: -0.1700

Data Index: 2039095 (Open Web Text)

Max Activating Token Index: 40

Text #8

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.3127. Min Act: -0.1700

Data Index: 1749281 (Open Web Text)

Max Activating Token Index: 283

Text #9

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.3239. Min Act: -0.1700

Data Index: 799634 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.3102. Min Act: -0.1700

Data Index: 4902926 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.2998. Min Act: -0.1700

Data Index: 4870439 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.3113. Min Act: -0.1700

Data Index: 6917362 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.2985. Min Act: -0.1700

Data Index: 5852053 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.2862. Min Act: -0.1700

Data Index: 1007647 (Open Web Text)

Max Activating Token Index: 299

Text #15

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.2815. Min Act: -0.1700

Data Index: 3621072 (Open Web Text)

Max Activating Token Index: 824

Text #16

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.2796. Min Act: -0.1700

Data Index: 1975632 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.2858. Min Act: -0.1700

Data Index: 461081 (Open Web Text)

Max Activating Token Index: 394

Text #18

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.2868. Min Act: -0.1700

Data Index: 5030309 (Open Web Text)

Max Activating Token Index: 982

Text #19

Max Range: 2.5327. Min Range: -2.5327

Max Act: 2.2862. Min Act: -0.1700

Data Index: 2237820 (Open Web Text)

Max Activating Token Index: 302