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

Dataset: Open Web Text

Neuron 1844 in Layer 5

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: 3.1392. Min Range: -3.1392

Max Act: 3.1392. Min Act: -0.1700

Data Index: 2103005 (Open Web Text)

Max Activating Token Index: 54

Text #1

Max Range: 3.1392. Min Range: -3.1392

Max Act: 3.0819. Min Act: -0.1700

Data Index: 2095400 (Open Web Text)

Max Activating Token Index: 819

Text #2

Max Range: 3.1392. Min Range: -3.1392

Max Act: 3.0379. Min Act: -0.1700

Data Index: 3305251 (Open Web Text)

Max Activating Token Index: 931

Text #3

Max Range: 3.1392. Min Range: -3.1392

Max Act: 3.0017. Min Act: -0.1700

Data Index: 1954936 (Open Web Text)

Max Activating Token Index: 652

Text #4

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.9978. Min Act: -0.1700

Data Index: 6966363 (Open Web Text)

Max Activating Token Index: 834

Text #5

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.9570. Min Act: -0.1700

Data Index: 8470825 (Open Web Text)

Max Activating Token Index: 184

Text #6

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.9788. Min Act: -0.1700

Data Index: 2656112 (Open Web Text)

Max Activating Token Index: 45

Text #7

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.9407. Min Act: -0.1700

Data Index: 6420949 (Open Web Text)

Max Activating Token Index: 594

Text #8

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.9165. Min Act: -0.1700

Data Index: 7209795 (Open Web Text)

Max Activating Token Index: 611

Text #9

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.9093. Min Act: -0.1700

Data Index: 6856635 (Open Web Text)

Max Activating Token Index: 510

Text #10

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.8931. Min Act: -0.1700

Data Index: 6053447 (Open Web Text)

Max Activating Token Index: 736

Text #11

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.8735. Min Act: -0.1700

Data Index: 4247250 (Open Web Text)

Max Activating Token Index: 626

Text #12

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.8777. Min Act: -0.1700

Data Index: 8758654 (Open Web Text)

Max Activating Token Index: 252

Text #13

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.8647. Min Act: -0.1700

Data Index: 7732261 (Open Web Text)

Max Activating Token Index: 707

Text #14

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.8444. Min Act: -0.1700

Data Index: 699069 (Open Web Text)

Max Activating Token Index: 989

Text #15

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.8690. Min Act: -0.1700

Data Index: 2855053 (Open Web Text)

Max Activating Token Index: 218

Text #16

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.8227. Min Act: -0.1700

Data Index: 1067337 (Open Web Text)

Max Activating Token Index: 772

Text #17

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.8728. Min Act: -0.1700

Data Index: 2697045 (Open Web Text)

Max Activating Token Index: 352

Text #18

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.8538. Min Act: -0.1700

Data Index: 1008671 (Open Web Text)

Max Activating Token Index: 898

Text #19

Max Range: 3.1392. Min Range: -3.1392

Max Act: 2.8325. Min Act: -0.1700

Data Index: 6224141 (Open Web Text)

Max Activating Token Index: 729