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

Dataset: Open Web Text

Neuron 89 in Layer 5

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: 3.7068. Min Range: -3.7068

Max Act: 3.7068. Min Act: -0.1700

Data Index: 2525025 (Open Web Text)

Max Activating Token Index: 837

Text #1

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.7048. Min Act: -0.1700

Data Index: 3460366 (Open Web Text)

Max Activating Token Index: 623

Text #2

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6832. Min Act: -0.1700

Data Index: 1815997 (Open Web Text)

Max Activating Token Index: 834

Text #3

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6939. Min Act: -0.1700

Data Index: 4533507 (Open Web Text)

Max Activating Token Index: 551

Text #4

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6747. Min Act: -0.1700

Data Index: 55276 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6430. Min Act: -0.1700

Data Index: 1746099 (Open Web Text)

Max Activating Token Index: 236

Text #6

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6431. Min Act: -0.1700

Data Index: 5947913 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6504. Min Act: -0.1700

Data Index: 8060692 (Open Web Text)

Max Activating Token Index: 176

Text #8

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6426. Min Act: -0.1700

Data Index: 7423532 (Open Web Text)

Max Activating Token Index: 486

Text #9

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6681. Min Act: -0.1700

Data Index: 4673221 (Open Web Text)

Max Activating Token Index: 69

Text #10

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6432. Min Act: -0.1700

Data Index: 7144163 (Open Web Text)

Max Activating Token Index: 336

Text #11

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6544. Min Act: -0.1700

Data Index: 3745444 (Open Web Text)

Max Activating Token Index: 657

Text #12

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6530. Min Act: -0.1700

Data Index: 627047 (Open Web Text)

Max Activating Token Index: 536

Text #13

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6562. Min Act: -0.1700

Data Index: 8519709 (Open Web Text)

Max Activating Token Index: 801

Text #14

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6171. Min Act: -0.1700

Data Index: 2684843 (Open Web Text)

Max Activating Token Index: 740

Text #15

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6326. Min Act: -0.1700

Data Index: 2539990 (Open Web Text)

Max Activating Token Index: 854

Text #16

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6374. Min Act: -0.1700

Data Index: 2387049 (Open Web Text)

Max Activating Token Index: 415

Text #17

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6356. Min Act: -0.1700

Data Index: 1358290 (Open Web Text)

Max Activating Token Index: 412

Text #18

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6373. Min Act: -0.1700

Data Index: 2502446 (Open Web Text)

Max Activating Token Index: 758

Text #19

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6485. Min Act: -0.1700

Data Index: 4376343 (Open Web Text)

Max Activating Token Index: 598