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

Dataset: Open Web Text

Neuron 2229 in Layer 4

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: 4.0414. Min Range: -4.0414

Max Act: 4.0414. Min Act: -0.1700

Data Index: 6844247 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9707. Min Act: -0.1700

Data Index: 3849045 (Open Web Text)

Max Activating Token Index: 196

Text #2

Max Range: 4.0414. Min Range: -4.0414

Max Act: 4.0018. Min Act: -0.1700

Data Index: 1497211 (Open Web Text)

Max Activating Token Index: 93

Text #3

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9560. Min Act: -0.1700

Data Index: 3983936 (Open Web Text)

Max Activating Token Index: 57

Text #4

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9993. Min Act: -0.1700

Data Index: 4040240 (Open Web Text)

Max Activating Token Index: 291

Text #5

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9924. Min Act: -0.1700

Data Index: 1452100 (Open Web Text)

Max Activating Token Index: 381

Text #6

Max Range: 4.0414. Min Range: -4.0414

Max Act: 4.0023. Min Act: -0.1700

Data Index: 2684868 (Open Web Text)

Max Activating Token Index: 210

Text #7

Max Range: 4.0414. Min Range: -4.0414

Max Act: 4.0159. Min Act: -0.1700

Data Index: 4532884 (Open Web Text)

Max Activating Token Index: 426

Text #8

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9331. Min Act: -0.1700

Data Index: 7367120 (Open Web Text)

Max Activating Token Index: 717

Text #9

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9487. Min Act: -0.1700

Data Index: 8559773 (Open Web Text)

Max Activating Token Index: 569

Text #10

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9651. Min Act: -0.1700

Data Index: 8170995 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9601. Min Act: -0.1700

Data Index: 5699043 (Open Web Text)

Max Activating Token Index: 539

Text #12

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.8950. Min Act: -0.1700

Data Index: 7191770 (Open Web Text)

Max Activating Token Index: 533

Text #13

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9559. Min Act: -0.1700

Data Index: 4329485 (Open Web Text)

Max Activating Token Index: 961

Text #14

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9624. Min Act: -0.1700

Data Index: 5838557 (Open Web Text)

Max Activating Token Index: 882

Text #15

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9411. Min Act: -0.1700

Data Index: 390176 (Open Web Text)

Max Activating Token Index: 777

Text #16

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9459. Min Act: -0.1700

Data Index: 3249092 (Open Web Text)

Max Activating Token Index: 596

Text #17

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9512. Min Act: -0.1700

Data Index: 5029128 (Open Web Text)

Max Activating Token Index: 538

Text #18

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9318. Min Act: -0.1700

Data Index: 1312778 (Open Web Text)

Max Activating Token Index: 860

Text #19

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9030. Min Act: -0.1700

Data Index: 5621974 (Open Web Text)

Max Activating Token Index: 980