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

Dataset: Open Web Text

Neuron 2199 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: 5.0540. Min Range: -5.0540

Max Act: 5.0540. Min Act: -0.1700

Data Index: 995534 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 5.0540. Min Range: -5.0540

Max Act: 5.0540. Min Act: -0.1700

Data Index: 4265363 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 5.0540. Min Range: -5.0540

Max Act: 5.0540. Min Act: -0.1700

Data Index: 5330450 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 5.0540. Min Range: -5.0540

Max Act: 5.0540. Min Act: -0.1700

Data Index: 5131858 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 5.0540. Min Range: -5.0540

Max Act: 5.0540. Min Act: -0.1700

Data Index: 1170272 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.0540. Min Range: -5.0540

Max Act: 5.0197. Min Act: -0.1700

Data Index: 2738553 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.0540. Min Range: -5.0540

Max Act: 5.0211. Min Act: -0.1700

Data Index: 4292882 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9450. Min Act: -0.1700

Data Index: 5849778 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9493. Min Act: -0.1700

Data Index: 40089 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9493. Min Act: -0.1700

Data Index: 2437191 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9325. Min Act: -0.1700

Data Index: 7100105 (Open Web Text)

Max Activating Token Index: 55

Text #11

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9493. Min Act: -0.1700

Data Index: 6373992 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9266. Min Act: -0.1700

Data Index: 6653202 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9150. Min Act: -0.1700

Data Index: 2553099 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9018. Min Act: -0.1700

Data Index: 3501565 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9048. Min Act: -0.1700

Data Index: 2758380 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9048. Min Act: -0.1700

Data Index: 782136 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9142. Min Act: -0.1700

Data Index: 826692 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.9166. Min Act: -0.1700

Data Index: 4076318 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.0540. Min Range: -5.0540

Max Act: 4.8927. Min Act: -0.1700

Data Index: 4161638 (Open Web Text)

Max Activating Token Index: 3