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

Dataset: Open Web Text

Neuron 3047 in Layer 4

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: 4.5339. Min Range: -4.5339

Max Act: 4.5339. Min Act: -0.1700

Data Index: 2403810 (Open Web Text)

Max Activating Token Index: 965

Text #1

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4681. Min Act: -0.1700

Data Index: 1280220 (Open Web Text)

Max Activating Token Index: 772

Text #2

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.5074. Min Act: -0.1700

Data Index: 928033 (Open Web Text)

Max Activating Token Index: 993

Text #3

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4083. Min Act: -0.1700

Data Index: 7571372 (Open Web Text)

Max Activating Token Index: 770

Text #4

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4069. Min Act: -0.1700

Data Index: 8260079 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4039. Min Act: -0.1700

Data Index: 6172795 (Open Web Text)

Max Activating Token Index: 598

Text #6

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4172. Min Act: -0.1700

Data Index: 8361876 (Open Web Text)

Max Activating Token Index: 610

Text #7

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4277. Min Act: -0.1700

Data Index: 2152415 (Open Web Text)

Max Activating Token Index: 844

Text #8

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.3769. Min Act: -0.1700

Data Index: 7102653 (Open Web Text)

Max Activating Token Index: 589

Text #9

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4236. Min Act: -0.1700

Data Index: 6849902 (Open Web Text)

Max Activating Token Index: 318

Text #10

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.3789. Min Act: -0.1700

Data Index: 216548 (Open Web Text)

Max Activating Token Index: 20

Text #11

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4338. Min Act: -0.1700

Data Index: 3507194 (Open Web Text)

Max Activating Token Index: 1015

Text #12

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4004. Min Act: -0.1700

Data Index: 105469 (Open Web Text)

Max Activating Token Index: 188

Text #13

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.3977. Min Act: -0.1700

Data Index: 3344174 (Open Web Text)

Max Activating Token Index: 918

Text #14

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.3859. Min Act: -0.1700

Data Index: 7777738 (Open Web Text)

Max Activating Token Index: 86

Text #15

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4087. Min Act: -0.1700

Data Index: 2907359 (Open Web Text)

Max Activating Token Index: 427

Text #16

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4063. Min Act: -0.1700

Data Index: 2004151 (Open Web Text)

Max Activating Token Index: 511

Text #17

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.4016. Min Act: -0.1700

Data Index: 1688380 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.3679. Min Act: -0.1700

Data Index: 4655017 (Open Web Text)

Max Activating Token Index: 765

Text #19

Max Range: 4.5339. Min Range: -4.5339

Max Act: 4.3863. Min Act: -0.1700

Data Index: 4837766 (Open Web Text)

Max Activating Token Index: 417