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

Dataset: Open Web Text

Neuron 903 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: 4.4535. Min Range: -4.4535

Max Act: 4.4396. Min Act: -0.1700

Data Index: 1634389 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4535. Min Act: -0.1700

Data Index: 2893237 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4429. Min Act: -0.1700

Data Index: 7378419 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4347. Min Act: -0.1700

Data Index: 7252619 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4308. Min Act: -0.1700

Data Index: 793277 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4172. Min Act: -0.1700

Data Index: 792589 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4146. Min Act: -0.1700

Data Index: 1563374 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4187. Min Act: -0.1700

Data Index: 1516532 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4128. Min Act: -0.1700

Data Index: 2384053 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4269. Min Act: -0.1700

Data Index: 4637953 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4220. Min Act: -0.1700

Data Index: 3894021 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.3906. Min Act: -0.1700

Data Index: 4118918 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.3975. Min Act: -0.1700

Data Index: 4096709 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4157. Min Act: -0.1700

Data Index: 479172 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.3921. Min Act: -0.1700

Data Index: 686015 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.3906. Min Act: -0.1700

Data Index: 5856190 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.3846. Min Act: -0.1700

Data Index: 224883 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.4102. Min Act: -0.1700

Data Index: 6127030 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.3960. Min Act: -0.1700

Data Index: 2026055 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.4535. Min Range: -4.4535

Max Act: 4.3889. Min Act: -0.1700

Data Index: 2765862 (Open Web Text)

Max Activating Token Index: 6