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

Dataset: Open Web Text

Neuron 1539 in Layer 6

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: 5.1047. Min Range: -5.1047

Max Act: 5.1047. Min Act: -0.1700

Data Index: 6899661 (Open Web Text)

Max Activating Token Index: 556

Text #1

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.9974. Min Act: -0.1700

Data Index: 3759711 (Open Web Text)

Max Activating Token Index: 924

Text #2

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.9531. Min Act: -0.1700

Data Index: 4618227 (Open Web Text)

Max Activating Token Index: 825

Text #3

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.9542. Min Act: -0.1700

Data Index: 1431496 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.9610. Min Act: -0.1700

Data Index: 113187 (Open Web Text)

Max Activating Token Index: 110

Text #5

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.8893. Min Act: -0.1700

Data Index: 4438693 (Open Web Text)

Max Activating Token Index: 426

Text #6

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.8997. Min Act: -0.1700

Data Index: 8169697 (Open Web Text)

Max Activating Token Index: 386

Text #7

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.8591. Min Act: -0.1700

Data Index: 1828407 (Open Web Text)

Max Activating Token Index: 910

Text #8

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.8395. Min Act: -0.1700

Data Index: 2868715 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.8413. Min Act: -0.1700

Data Index: 3062202 (Open Web Text)

Max Activating Token Index: 222

Text #10

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.8715. Min Act: -0.1700

Data Index: 5856793 (Open Web Text)

Max Activating Token Index: 852

Text #11

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.8380. Min Act: -0.1700

Data Index: 21270 (Open Web Text)

Max Activating Token Index: 866

Text #12

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.7969. Min Act: -0.1700

Data Index: 621517 (Open Web Text)

Max Activating Token Index: 845

Text #13

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.7909. Min Act: -0.1700

Data Index: 5487885 (Open Web Text)

Max Activating Token Index: 734

Text #14

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.7957. Min Act: -0.1700

Data Index: 4440052 (Open Web Text)

Max Activating Token Index: 179

Text #15

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.7735. Min Act: -0.1700

Data Index: 4310843 (Open Web Text)

Max Activating Token Index: 453

Text #16

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.7591. Min Act: -0.1700

Data Index: 5364210 (Open Web Text)

Max Activating Token Index: 334

Text #17

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.7307. Min Act: -0.1700

Data Index: 7731047 (Open Web Text)

Max Activating Token Index: 368

Text #18

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.6958. Min Act: -0.1700

Data Index: 6530602 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 5.1047. Min Range: -5.1047

Max Act: 4.6954. Min Act: -0.1700

Data Index: 754811 (Open Web Text)

Max Activating Token Index: 670