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

Dataset: Open Web Text

Neuron 1944 in Layer 1

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: 0.7514. Min Range: -0.7514

Max Act: 0.7514. Min Act: -0.1061

Data Index: 5100452 (Open Web Text)

Max Activating Token Index: 46

Text #1

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7372. Min Act: -0.0772

Data Index: 4363759 (Open Web Text)

Max Activating Token Index: 45

Text #2

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7473. Min Act: -0.0680

Data Index: 890712 (Open Web Text)

Max Activating Token Index: 25

Text #3

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7345. Min Act: -0.0912

Data Index: 6663268 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7366. Min Act: -0.0964

Data Index: 2259066 (Open Web Text)

Max Activating Token Index: 66

Text #5

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7321. Min Act: -0.0904

Data Index: 5460422 (Open Web Text)

Max Activating Token Index: 55

Text #6

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7428. Min Act: -0.1162

Data Index: 4995820 (Open Web Text)

Max Activating Token Index: 46

Text #7

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7238. Min Act: -0.0734

Data Index: 2734922 (Open Web Text)

Max Activating Token Index: 47

Text #8

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7270. Min Act: -0.0460

Data Index: 890271 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7317. Min Act: -0.0823

Data Index: 2797166 (Open Web Text)

Max Activating Token Index: 37

Text #10

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7223. Min Act: -0.1000

Data Index: 4628659 (Open Web Text)

Max Activating Token Index: 53

Text #11

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7226. Min Act: -0.0709

Data Index: 4478338 (Open Web Text)

Max Activating Token Index: 43

Text #12

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7160. Min Act: -0.0500

Data Index: 4847070 (Open Web Text)

Max Activating Token Index: 47

Text #13

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7126. Min Act: -0.0731

Data Index: 805067 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7130. Min Act: -0.0741

Data Index: 13226 (Open Web Text)

Max Activating Token Index: 41

Text #15

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7156. Min Act: -0.0946

Data Index: 5702472 (Open Web Text)

Max Activating Token Index: 44

Text #16

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7129. Min Act: -0.0953

Data Index: 8529025 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7078. Min Act: -0.0997

Data Index: 2198172 (Open Web Text)

Max Activating Token Index: 70

Text #18

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7141. Min Act: -0.0950

Data Index: 1995907 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7081. Min Act: -0.0756

Data Index: 8369265 (Open Web Text)

Max Activating Token Index: 39