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

Dataset: Open Web Text

Neuron 2953 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: 4.2257. Min Range: -4.2257

Max Act: 4.2257. Min Act: -0.1700

Data Index: 5405703 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.2257. Min Range: -4.2257

Max Act: 4.1285. Min Act: -0.1700

Data Index: 3407575 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.2257. Min Range: -4.2257

Max Act: 4.0945. Min Act: -0.1700

Data Index: 2225663 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.2257. Min Range: -4.2257

Max Act: 4.0945. Min Act: -0.1700

Data Index: 5047023 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.2257. Min Range: -4.2257

Max Act: 4.0614. Min Act: -0.1700

Data Index: 2817174 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.2257. Min Range: -4.2257

Max Act: 4.0458. Min Act: -0.1700

Data Index: 5594587 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.2257. Min Range: -4.2257

Max Act: 4.0034. Min Act: -0.1700

Data Index: 7565080 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.2257. Min Range: -4.2257

Max Act: 4.0173. Min Act: -0.1700

Data Index: 7979953 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.2257. Min Range: -4.2257

Max Act: 4.0034. Min Act: -0.1700

Data Index: 4406629 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.9729. Min Act: -0.1700

Data Index: 4879588 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.9735. Min Act: -0.1700

Data Index: 2531999 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.9810. Min Act: -0.1700

Data Index: 6182791 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.9913. Min Act: -0.1700

Data Index: 1337702 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.9492. Min Act: -0.1700

Data Index: 6526264 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.9643. Min Act: -0.1700

Data Index: 7574453 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.9578. Min Act: -0.1700

Data Index: 8081964 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.9705. Min Act: -0.1700

Data Index: 6461473 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.9660. Min Act: -0.1700

Data Index: 8218729 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.9525. Min Act: -0.1700

Data Index: 8378723 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.9660. Min Act: -0.1700

Data Index: 8629324 (Open Web Text)

Max Activating Token Index: 3