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

Dataset: Open Web Text

Neuron 1497 in Layer 3

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: 4.6488. Min Range: -4.6488

Max Act: 4.6488. Min Act: -0.1700

Data Index: 1928268 (Open Web Text)

Max Activating Token Index: 134

Text #1

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.6256. Min Act: -0.1700

Data Index: 2016484 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.6159. Min Act: -0.1700

Data Index: 8174703 (Open Web Text)

Max Activating Token Index: 205

Text #3

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5920. Min Act: -0.1700

Data Index: 3985427 (Open Web Text)

Max Activating Token Index: 574

Text #4

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5581. Min Act: -0.1700

Data Index: 7563071 (Open Web Text)

Max Activating Token Index: 845

Text #5

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5418. Min Act: -0.1700

Data Index: 540086 (Open Web Text)

Max Activating Token Index: 69

Text #6

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5277. Min Act: -0.1700

Data Index: 5292174 (Open Web Text)

Max Activating Token Index: 969

Text #7

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5474. Min Act: -0.1700

Data Index: 5060925 (Open Web Text)

Max Activating Token Index: 175

Text #8

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5465. Min Act: -0.1700

Data Index: 8524840 (Open Web Text)

Max Activating Token Index: 267

Text #9

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5323. Min Act: -0.1700

Data Index: 1220848 (Open Web Text)

Max Activating Token Index: 698

Text #10

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5073. Min Act: -0.1700

Data Index: 3798702 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5249. Min Act: -0.1700

Data Index: 4667655 (Open Web Text)

Max Activating Token Index: 239

Text #12

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5296. Min Act: -0.1700

Data Index: 7751865 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5419. Min Act: -0.1700

Data Index: 8755829 (Open Web Text)

Max Activating Token Index: 619

Text #14

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5062. Min Act: -0.1700

Data Index: 3693207 (Open Web Text)

Max Activating Token Index: 357

Text #15

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.4771. Min Act: -0.1700

Data Index: 5089047 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.4910. Min Act: -0.1700

Data Index: 4781818 (Open Web Text)

Max Activating Token Index: 459

Text #17

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5048. Min Act: -0.1700

Data Index: 8228617 (Open Web Text)

Max Activating Token Index: 492

Text #18

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5167. Min Act: -0.1700

Data Index: 8310900 (Open Web Text)

Max Activating Token Index: 605

Text #19

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.4848. Min Act: -0.1700

Data Index: 3131012 (Open Web Text)

Max Activating Token Index: 193