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

Dataset: Open Web Text

Neuron 785 in Layer 2

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: 4.2042. Min Range: -4.2042

Max Act: 4.2042. Min Act: -0.1700

Data Index: 3168194 (Open Web Text)

Max Activating Token Index: 379

Text #1

Max Range: 4.2042. Min Range: -4.2042

Max Act: 4.0133. Min Act: -0.1700

Data Index: 5805350 (Open Web Text)

Max Activating Token Index: 269

Text #2

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9855. Min Act: -0.1700

Data Index: 6121402 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9777. Min Act: -0.1700

Data Index: 1655233 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9862. Min Act: -0.1700

Data Index: 2118176 (Open Web Text)

Max Activating Token Index: 129

Text #5

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9750. Min Act: -0.1700

Data Index: 5393319 (Open Web Text)

Max Activating Token Index: 448

Text #6

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9563. Min Act: -0.1700

Data Index: 6382082 (Open Web Text)

Max Activating Token Index: 428

Text #7

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9369. Min Act: -0.1700

Data Index: 6177675 (Open Web Text)

Max Activating Token Index: 797

Text #8

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9595. Min Act: -0.1700

Data Index: 5971390 (Open Web Text)

Max Activating Token Index: 329

Text #9

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9293. Min Act: -0.1700

Data Index: 3751174 (Open Web Text)

Max Activating Token Index: 742

Text #10

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9244. Min Act: -0.1700

Data Index: 3776053 (Open Web Text)

Max Activating Token Index: 689

Text #11

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9194. Min Act: -0.1700

Data Index: 3778871 (Open Web Text)

Max Activating Token Index: 423

Text #12

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9260. Min Act: -0.1700

Data Index: 5172173 (Open Web Text)

Max Activating Token Index: 571

Text #13

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.9098. Min Act: -0.1700

Data Index: 8659509 (Open Web Text)

Max Activating Token Index: 467

Text #14

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.8939. Min Act: -0.1700

Data Index: 5509467 (Open Web Text)

Max Activating Token Index: 540

Text #15

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.8915. Min Act: -0.1700

Data Index: 3776054 (Open Web Text)

Max Activating Token Index: 374

Text #16

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.8764. Min Act: -0.1700

Data Index: 5175226 (Open Web Text)

Max Activating Token Index: 421

Text #17

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.8711. Min Act: -0.1700

Data Index: 6020834 (Open Web Text)

Max Activating Token Index: 211

Text #18

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.8853. Min Act: -0.1700

Data Index: 5356892 (Open Web Text)

Max Activating Token Index: 1002

Text #19

Max Range: 4.2042. Min Range: -4.2042

Max Act: 3.8754. Min Act: -0.1700

Data Index: 923233 (Open Web Text)

Max Activating Token Index: 867