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

Dataset: Open Web Text

Neuron 1514 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: 3.5972. Min Range: -3.5972

Max Act: 3.5972. Min Act: -0.1700

Data Index: 8076574 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5548. Min Act: -0.1700

Data Index: 5401374 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5420. Min Act: -0.1700

Data Index: 948551 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5392. Min Act: -0.1700

Data Index: 3062055 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5290. Min Act: -0.1700

Data Index: 4648553 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5172. Min Act: -0.1700

Data Index: 4026485 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5199. Min Act: -0.1700

Data Index: 4003905 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5177. Min Act: -0.1700

Data Index: 39039 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5057. Min Act: -0.1700

Data Index: 3474791 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5183. Min Act: -0.1700

Data Index: 2947448 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5233. Min Act: -0.1700

Data Index: 8103496 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5222. Min Act: -0.1700

Data Index: 1899165 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5250. Min Act: -0.1700

Data Index: 2529646 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5153. Min Act: -0.1700

Data Index: 2390422 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.4893. Min Act: -0.1700

Data Index: 2110119 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.4806. Min Act: -0.1700

Data Index: 3481501 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.4793. Min Act: -0.1700

Data Index: 3640085 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.4823. Min Act: -0.1700

Data Index: 2319228 (Open Web Text)

Max Activating Token Index: 37

Text #18

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.5099. Min Act: -0.1700

Data Index: 2341952 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.5972. Min Range: -3.5972

Max Act: 3.4879. Min Act: -0.1700

Data Index: 1502563 (Open Web Text)

Max Activating Token Index: 7