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

Dataset: Open Web Text

Neuron 1063 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: 2.9874. Min Range: -2.9874

Max Act: 2.9874. Min Act: -0.1700

Data Index: 8083234 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.9672. Min Act: -0.1700

Data Index: 462239 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.9286. Min Act: -0.1700

Data Index: 3514565 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.9342. Min Act: -0.1700

Data Index: 8049134 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.9113. Min Act: -0.1700

Data Index: 725537 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.9164. Min Act: -0.1700

Data Index: 5963150 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.9216. Min Act: -0.1700

Data Index: 556310 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.9068. Min Act: -0.1700

Data Index: 7401120 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.9063. Min Act: -0.1700

Data Index: 813737 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.8825. Min Act: -0.1700

Data Index: 2253989 (Open Web Text)

Max Activating Token Index: 262

Text #10

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.8869. Min Act: -0.1700

Data Index: 849378 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.8701. Min Act: -0.1700

Data Index: 7355111 (Open Web Text)

Max Activating Token Index: 40

Text #12

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.8735. Min Act: -0.1700

Data Index: 5205400 (Open Web Text)

Max Activating Token Index: 113

Text #13

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.8757. Min Act: -0.1700

Data Index: 3874859 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.8621. Min Act: -0.1700

Data Index: 1875551 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.8758. Min Act: -0.1700

Data Index: 383797 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.8617. Min Act: -0.1700

Data Index: 2999040 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.8643. Min Act: -0.1700

Data Index: 6204898 (Open Web Text)

Max Activating Token Index: 193

Text #18

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.8512. Min Act: -0.1700

Data Index: 6778887 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 2.9874. Min Range: -2.9874

Max Act: 2.8575. Min Act: -0.1700

Data Index: 4589202 (Open Web Text)

Max Activating Token Index: 2