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

Dataset: Open Web Text

Neuron 2241 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: 5.1531. Min Range: -5.1531

Max Act: 5.1531. Min Act: -0.1700

Data Index: 2294301 (Open Web Text)

Max Activating Token Index: 757

Text #1

Max Range: 5.1531. Min Range: -5.1531

Max Act: 5.1145. Min Act: -0.1700

Data Index: 4654540 (Open Web Text)

Max Activating Token Index: 757

Text #2

Max Range: 5.1531. Min Range: -5.1531

Max Act: 5.0339. Min Act: -0.1700

Data Index: 6321931 (Open Web Text)

Max Activating Token Index: 997

Text #3

Max Range: 5.1531. Min Range: -5.1531

Max Act: 5.0785. Min Act: -0.1700

Data Index: 636799 (Open Web Text)

Max Activating Token Index: 887

Text #4

Max Range: 5.1531. Min Range: -5.1531

Max Act: 5.0890. Min Act: -0.1700

Data Index: 4697265 (Open Web Text)

Max Activating Token Index: 809

Text #5

Max Range: 5.1531. Min Range: -5.1531

Max Act: 5.0987. Min Act: -0.1700

Data Index: 8331975 (Open Web Text)

Max Activating Token Index: 958

Text #6

Max Range: 5.1531. Min Range: -5.1531

Max Act: 5.0510. Min Act: -0.1700

Data Index: 809811 (Open Web Text)

Max Activating Token Index: 458

Text #7

Max Range: 5.1531. Min Range: -5.1531

Max Act: 5.0410. Min Act: -0.1700

Data Index: 1417832 (Open Web Text)

Max Activating Token Index: 892

Text #8

Max Range: 5.1531. Min Range: -5.1531

Max Act: 5.0364. Min Act: -0.1700

Data Index: 8561919 (Open Web Text)

Max Activating Token Index: 520

Text #9

Max Range: 5.1531. Min Range: -5.1531

Max Act: 4.9904. Min Act: -0.1700

Data Index: 8725685 (Open Web Text)

Max Activating Token Index: 564

Text #10

Max Range: 5.1531. Min Range: -5.1531

Max Act: 5.0135. Min Act: -0.1700

Data Index: 669714 (Open Web Text)

Max Activating Token Index: 311

Text #11

Max Range: 5.1531. Min Range: -5.1531

Max Act: 5.0150. Min Act: -0.1700

Data Index: 1811137 (Open Web Text)

Max Activating Token Index: 94

Text #12

Max Range: 5.1531. Min Range: -5.1531

Max Act: 4.9453. Min Act: -0.1700

Data Index: 8068471 (Open Web Text)

Max Activating Token Index: 475

Text #13

Max Range: 5.1531. Min Range: -5.1531

Max Act: 4.9822. Min Act: -0.1700

Data Index: 2525690 (Open Web Text)

Max Activating Token Index: 953

Text #14

Max Range: 5.1531. Min Range: -5.1531

Max Act: 4.9383. Min Act: -0.1700

Data Index: 8021038 (Open Web Text)

Max Activating Token Index: 906

Text #15

Max Range: 5.1531. Min Range: -5.1531

Max Act: 4.9979. Min Act: -0.1700

Data Index: 3574221 (Open Web Text)

Max Activating Token Index: 502

Text #16

Max Range: 5.1531. Min Range: -5.1531

Max Act: 4.9515. Min Act: -0.1700

Data Index: 1236962 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 5.1531. Min Range: -5.1531

Max Act: 4.9588. Min Act: -0.1700

Data Index: 395873 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 5.1531. Min Range: -5.1531

Max Act: 4.9264. Min Act: -0.1700

Data Index: 4401323 (Open Web Text)

Max Activating Token Index: 843

Text #19

Max Range: 5.1531. Min Range: -5.1531

Max Act: 4.9581. Min Act: -0.1700

Data Index: 6440211 (Open Web Text)

Max Activating Token Index: 764