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

Dataset: Open Web Text

Neuron 1703 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: 4.1435. Min Range: -4.1435

Max Act: 4.1369. Min Act: -0.1700

Data Index: 3004240 (Open Web Text)

Max Activating Token Index: 37

Text #1

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.1089. Min Act: -0.1700

Data Index: 4628460 (Open Web Text)

Max Activating Token Index: 994

Text #2

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.1435. Min Act: -0.1700

Data Index: 3461291 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.1255. Min Act: -0.1700

Data Index: 8326755 (Open Web Text)

Max Activating Token Index: 929

Text #4

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.0840. Min Act: -0.1700

Data Index: 2175001 (Open Web Text)

Max Activating Token Index: 971

Text #5

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.0805. Min Act: -0.1700

Data Index: 1931107 (Open Web Text)

Max Activating Token Index: 65

Text #6

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.0660. Min Act: -0.1700

Data Index: 2719949 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.0819. Min Act: -0.1700

Data Index: 4687071 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.0609. Min Act: -0.1700

Data Index: 2314170 (Open Web Text)

Max Activating Token Index: 119

Text #9

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.0000. Min Act: -0.1700

Data Index: 5932303 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.0123. Min Act: -0.1700

Data Index: 5323199 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.0286. Min Act: -0.1700

Data Index: 4898893 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.0209. Min Act: -0.1700

Data Index: 7437038 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 4.1435. Min Range: -4.1435

Max Act: 3.9948. Min Act: -0.1700

Data Index: 6267332 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 4.1435. Min Range: -4.1435

Max Act: 4.0426. Min Act: -0.1700

Data Index: 4376306 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.1435. Min Range: -4.1435

Max Act: 3.9999. Min Act: -0.1700

Data Index: 4057029 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.1435. Min Range: -4.1435

Max Act: 3.9873. Min Act: -0.1700

Data Index: 6047552 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.1435. Min Range: -4.1435

Max Act: 3.9739. Min Act: -0.1700

Data Index: 3860329 (Open Web Text)

Max Activating Token Index: 674

Text #18

Max Range: 4.1435. Min Range: -4.1435

Max Act: 3.9616. Min Act: -0.1700

Data Index: 422556 (Open Web Text)

Max Activating Token Index: 895

Text #19

Max Range: 4.1435. Min Range: -4.1435

Max Act: 3.9504. Min Act: -0.1700

Data Index: 388106 (Open Web Text)

Max Activating Token Index: 916