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

Dataset: Open Web Text

Neuron 1708 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: 4.1267. Min Range: -4.1267

Max Act: 4.0705. Min Act: -0.1700

Data Index: 5082851 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 4.1267. Min Range: -4.1267

Max Act: 4.1267. Min Act: -0.1700

Data Index: 1004095 (Open Web Text)

Max Activating Token Index: 146

Text #2

Max Range: 4.1267. Min Range: -4.1267

Max Act: 4.0908. Min Act: -0.1700

Data Index: 3623960 (Open Web Text)

Max Activating Token Index: 615

Text #3

Max Range: 4.1267. Min Range: -4.1267

Max Act: 4.0786. Min Act: -0.1700

Data Index: 2739073 (Open Web Text)

Max Activating Token Index: 229

Text #4

Max Range: 4.1267. Min Range: -4.1267

Max Act: 4.1169. Min Act: -0.1700

Data Index: 1214402 (Open Web Text)

Max Activating Token Index: 1017

Text #5

Max Range: 4.1267. Min Range: -4.1267

Max Act: 4.0913. Min Act: -0.1700

Data Index: 7615589 (Open Web Text)

Max Activating Token Index: 256

Text #6

Max Range: 4.1267. Min Range: -4.1267

Max Act: 4.0420. Min Act: -0.1700

Data Index: 2489172 (Open Web Text)

Max Activating Token Index: 491

Text #7

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.9564. Min Act: -0.1700

Data Index: 2463863 (Open Web Text)

Max Activating Token Index: 740

Text #8

Max Range: 4.1267. Min Range: -4.1267

Max Act: 4.0170. Min Act: -0.1700

Data Index: 8301589 (Open Web Text)

Max Activating Token Index: 663

Text #9

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.9896. Min Act: -0.1700

Data Index: 2749092 (Open Web Text)

Max Activating Token Index: 530

Text #10

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.9524. Min Act: -0.1700

Data Index: 2094434 (Open Web Text)

Max Activating Token Index: 224

Text #11

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.8975. Min Act: -0.1700

Data Index: 3916088 (Open Web Text)

Max Activating Token Index: 954

Text #12

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.9179. Min Act: -0.1700

Data Index: 5845224 (Open Web Text)

Max Activating Token Index: 819

Text #13

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.9317. Min Act: -0.1700

Data Index: 3882699 (Open Web Text)

Max Activating Token Index: 262

Text #14

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.8821. Min Act: -0.1700

Data Index: 4591747 (Open Web Text)

Max Activating Token Index: 430

Text #15

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.9070. Min Act: -0.1700

Data Index: 5721138 (Open Web Text)

Max Activating Token Index: 186

Text #16

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.8894. Min Act: -0.1700

Data Index: 2668125 (Open Web Text)

Max Activating Token Index: 365

Text #17

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.8638. Min Act: -0.1700

Data Index: 1583373 (Open Web Text)

Max Activating Token Index: 340

Text #18

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.8901. Min Act: -0.1700

Data Index: 6750791 (Open Web Text)

Max Activating Token Index: 574

Text #19

Max Range: 4.1267. Min Range: -4.1267

Max Act: 3.8897. Min Act: -0.1700

Data Index: 4154306 (Open Web Text)

Max Activating Token Index: 565