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

Dataset: Open Web Text

Neuron 2491 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: 3.7530. Min Range: -3.7530

Max Act: 3.7530. Min Act: -0.1700

Data Index: 4846104 (Open Web Text)

Max Activating Token Index: 481

Text #1

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.7147. Min Act: -0.1700

Data Index: 6165608 (Open Web Text)

Max Activating Token Index: 508

Text #2

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.7224. Min Act: -0.1700

Data Index: 4062764 (Open Web Text)

Max Activating Token Index: 172

Text #3

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.6808. Min Act: -0.1700

Data Index: 7104437 (Open Web Text)

Max Activating Token Index: 353

Text #4

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.6709. Min Act: -0.1700

Data Index: 2862357 (Open Web Text)

Max Activating Token Index: 345

Text #5

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.6337. Min Act: -0.1700

Data Index: 7693527 (Open Web Text)

Max Activating Token Index: 384

Text #6

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.6133. Min Act: -0.1700

Data Index: 4035282 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5713. Min Act: -0.1700

Data Index: 1305093 (Open Web Text)

Max Activating Token Index: 1020

Text #8

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5752. Min Act: -0.1700

Data Index: 1448836 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5475. Min Act: -0.1700

Data Index: 7214050 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5429. Min Act: -0.1700

Data Index: 6617898 (Open Web Text)

Max Activating Token Index: 897

Text #11

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5420. Min Act: -0.1700

Data Index: 2911658 (Open Web Text)

Max Activating Token Index: 87

Text #12

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5451. Min Act: -0.1700

Data Index: 8140808 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5596. Min Act: -0.1700

Data Index: 1389103 (Open Web Text)

Max Activating Token Index: 996

Text #14

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5708. Min Act: -0.1700

Data Index: 4521366 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5388. Min Act: -0.1700

Data Index: 1470306 (Open Web Text)

Max Activating Token Index: 432

Text #16

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5057. Min Act: -0.1700

Data Index: 3761116 (Open Web Text)

Max Activating Token Index: 84

Text #17

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5733. Min Act: -0.1700

Data Index: 1817916 (Open Web Text)

Max Activating Token Index: 522

Text #18

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5224. Min Act: -0.1700

Data Index: 5025400 (Open Web Text)

Max Activating Token Index: 426

Text #19

Max Range: 3.7530. Min Range: -3.7530

Max Act: 3.5476. Min Act: -0.1700

Data Index: 6687771 (Open Web Text)

Max Activating Token Index: 667