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

Dataset: Open Web Text

Neuron 2734 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: 5.6395. Min Range: -5.6395

Max Act: 5.6395. Min Act: -0.1700

Data Index: 6510830 (Open Web Text)

Max Activating Token Index: 634

Text #1

Max Range: 5.6395. Min Range: -5.6395

Max Act: 5.1862. Min Act: -0.1700

Data Index: 5112892 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.9168. Min Act: -0.1700

Data Index: 7883044 (Open Web Text)

Max Activating Token Index: 35

Text #3

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.8784. Min Act: -0.1700

Data Index: 8092337 (Open Web Text)

Max Activating Token Index: 159

Text #4

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.9049. Min Act: -0.1700

Data Index: 5414961 (Open Web Text)

Max Activating Token Index: 164

Text #5

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.8160. Min Act: -0.1700

Data Index: 8103553 (Open Web Text)

Max Activating Token Index: 53

Text #6

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.8021. Min Act: -0.1700

Data Index: 4286172 (Open Web Text)

Max Activating Token Index: 557

Text #7

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.7915. Min Act: -0.1700

Data Index: 4381574 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.7960. Min Act: -0.1700

Data Index: 4214118 (Open Web Text)

Max Activating Token Index: 95

Text #9

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.7676. Min Act: -0.1700

Data Index: 2148189 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.7217. Min Act: -0.1700

Data Index: 3394987 (Open Web Text)

Max Activating Token Index: 39

Text #11

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.6949. Min Act: -0.1700

Data Index: 7688706 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.6890. Min Act: -0.1700

Data Index: 246184 (Open Web Text)

Max Activating Token Index: 122

Text #13

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.6517. Min Act: -0.1700

Data Index: 1771036 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.6410. Min Act: -0.1700

Data Index: 8341725 (Open Web Text)

Max Activating Token Index: 834

Text #15

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.6560. Min Act: -0.1700

Data Index: 5415005 (Open Web Text)

Max Activating Token Index: 764

Text #16

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.6182. Min Act: -0.1700

Data Index: 4381214 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.6067. Min Act: -0.1700

Data Index: 1611363 (Open Web Text)

Max Activating Token Index: 107

Text #18

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.6000. Min Act: -0.1700

Data Index: 433953 (Open Web Text)

Max Activating Token Index: 238

Text #19

Max Range: 5.6395. Min Range: -5.6395

Max Act: 4.6108. Min Act: -0.1700

Data Index: 536262 (Open Web Text)

Max Activating Token Index: 568