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

Dataset: Open Web Text

Neuron 175 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: 3.9323. Min Range: -3.9323

Max Act: 3.9323. Min Act: -0.1700

Data Index: 357819 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.7562. Min Act: -0.1700

Data Index: 5276931 (Open Web Text)

Max Activating Token Index: 309

Text #2

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.6460. Min Act: -0.1700

Data Index: 5270808 (Open Web Text)

Max Activating Token Index: 215

Text #3

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.6673. Min Act: -0.1700

Data Index: 3866766 (Open Web Text)

Max Activating Token Index: 227

Text #4

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.6346. Min Act: -0.1700

Data Index: 3325149 (Open Web Text)

Max Activating Token Index: 193

Text #5

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.6243. Min Act: -0.1700

Data Index: 169818 (Open Web Text)

Max Activating Token Index: 174

Text #6

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.6070. Min Act: -0.1700

Data Index: 879620 (Open Web Text)

Max Activating Token Index: 515

Text #7

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5970. Min Act: -0.1700

Data Index: 3828268 (Open Web Text)

Max Activating Token Index: 92

Text #8

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5900. Min Act: -0.1700

Data Index: 4310195 (Open Web Text)

Max Activating Token Index: 111

Text #9

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5786. Min Act: -0.1700

Data Index: 654238 (Open Web Text)

Max Activating Token Index: 120

Text #10

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5566. Min Act: -0.1700

Data Index: 5495020 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5560. Min Act: -0.1700

Data Index: 5503725 (Open Web Text)

Max Activating Token Index: 568

Text #12

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5446. Min Act: -0.1700

Data Index: 7110623 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5614. Min Act: -0.1700

Data Index: 975398 (Open Web Text)

Max Activating Token Index: 296

Text #14

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5580. Min Act: -0.1700

Data Index: 1387289 (Open Web Text)

Max Activating Token Index: 615

Text #15

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5371. Min Act: -0.1700

Data Index: 53257 (Open Web Text)

Max Activating Token Index: 34

Text #16

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5357. Min Act: -0.1700

Data Index: 5933365 (Open Web Text)

Max Activating Token Index: 285

Text #17

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5322. Min Act: -0.1700

Data Index: 2755885 (Open Web Text)

Max Activating Token Index: 258

Text #18

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5332. Min Act: -0.1700

Data Index: 3330352 (Open Web Text)

Max Activating Token Index: 224

Text #19

Max Range: 3.9323. Min Range: -3.9323

Max Act: 3.5412. Min Act: -0.1700

Data Index: 6995760 (Open Web Text)

Max Activating Token Index: 103