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

Dataset: Open Web Text

Neuron 2910 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: 3.1529. Min Range: -3.1529

Max Act: 3.1529. Min Act: -0.1700

Data Index: 4587558 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.1419. Min Act: -0.1700

Data Index: 6956045 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.1363. Min Act: -0.1700

Data Index: 2802325 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.1380. Min Act: -0.1700

Data Index: 3448582 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.1327. Min Act: -0.1700

Data Index: 7692828 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.1187. Min Act: -0.1700

Data Index: 4863914 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.1352. Min Act: -0.1700

Data Index: 5565119 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.1154. Min Act: -0.1700

Data Index: 3221876 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.1127. Min Act: -0.1700

Data Index: 6100505 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.1143. Min Act: -0.1700

Data Index: 1284913 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0863. Min Act: -0.1700

Data Index: 6454767 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0913. Min Act: -0.1700

Data Index: 2437420 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0920. Min Act: -0.1700

Data Index: 132429 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0902. Min Act: -0.1700

Data Index: 590845 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0991. Min Act: -0.1700

Data Index: 1834346 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0733. Min Act: -0.1700

Data Index: 3779786 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0729. Min Act: -0.1700

Data Index: 8407266 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0749. Min Act: -0.1700

Data Index: 189912 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0681. Min Act: -0.1700

Data Index: 3984356 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0681. Min Act: -0.1700

Data Index: 3023603 (Open Web Text)

Max Activating Token Index: 11