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

Dataset: Open Web Text

Neuron 597 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: 4.4637. Min Range: -4.4637

Max Act: 4.4637. Min Act: -0.1700

Data Index: 5578655 (Open Web Text)

Max Activating Token Index: 756

Text #1

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.2890. Min Act: -0.1700

Data Index: 3826371 (Open Web Text)

Max Activating Token Index: 386

Text #2

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.3222. Min Act: -0.1700

Data Index: 8690760 (Open Web Text)

Max Activating Token Index: 602

Text #3

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.2616. Min Act: -0.1700

Data Index: 8099125 (Open Web Text)

Max Activating Token Index: 309

Text #4

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.2164. Min Act: -0.1700

Data Index: 6830467 (Open Web Text)

Max Activating Token Index: 603

Text #5

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.2301. Min Act: -0.1699

Data Index: 1944089 (Open Web Text)

Max Activating Token Index: 702

Text #6

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.2210. Min Act: -0.1700

Data Index: 8499690 (Open Web Text)

Max Activating Token Index: 688

Text #7

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.1337. Min Act: -0.1700

Data Index: 5889826 (Open Web Text)

Max Activating Token Index: 555

Text #8

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.1865. Min Act: -0.1700

Data Index: 5189215 (Open Web Text)

Max Activating Token Index: 732

Text #9

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.1202. Min Act: -0.1700

Data Index: 5722502 (Open Web Text)

Max Activating Token Index: 556

Text #10

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.1119. Min Act: -0.1700

Data Index: 5828847 (Open Web Text)

Max Activating Token Index: 170

Text #11

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.2365. Min Act: -0.1700

Data Index: 4250586 (Open Web Text)

Max Activating Token Index: 66

Text #12

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.1165. Min Act: -0.1700

Data Index: 7164492 (Open Web Text)

Max Activating Token Index: 156

Text #13

Max Range: 4.4637. Min Range: -4.4637

Max Act: 3.9618. Min Act: -0.1700

Data Index: 3589772 (Open Web Text)

Max Activating Token Index: 592

Text #14

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.1598. Min Act: -0.1700

Data Index: 3255680 (Open Web Text)

Max Activating Token Index: 722

Text #15

Max Range: 4.4637. Min Range: -4.4637

Max Act: 3.9987. Min Act: -0.1700

Data Index: 7251223 (Open Web Text)

Max Activating Token Index: 224

Text #16

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.0609. Min Act: -0.1700

Data Index: 7399064 (Open Web Text)

Max Activating Token Index: 660

Text #17

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.0304. Min Act: -0.1700

Data Index: 255165 (Open Web Text)

Max Activating Token Index: 630

Text #18

Max Range: 4.4637. Min Range: -4.4637

Max Act: 4.0158. Min Act: -0.1700

Data Index: 820004 (Open Web Text)

Max Activating Token Index: 406

Text #19

Max Range: 4.4637. Min Range: -4.4637

Max Act: 3.9849. Min Act: -0.1699

Data Index: 8445270 (Open Web Text)

Max Activating Token Index: 658