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

Dataset: Open Web Text

Neuron 996 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: 4.0338. Min Range: -4.0338

Max Act: 4.0338. Min Act: -0.1700

Data Index: 5435702 (Open Web Text)

Max Activating Token Index: 263

Text #1

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.9722. Min Act: -0.1700

Data Index: 6732638 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8995. Min Act: -0.1700

Data Index: 5675869 (Open Web Text)

Max Activating Token Index: 149

Text #3

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.9425. Min Act: -0.1700

Data Index: 5675868 (Open Web Text)

Max Activating Token Index: 171

Text #4

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.9510. Min Act: -0.1700

Data Index: 1980927 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.9089. Min Act: -0.1700

Data Index: 5435704 (Open Web Text)

Max Activating Token Index: 532

Text #6

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8967. Min Act: -0.1700

Data Index: 6023062 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.9113. Min Act: -0.1700

Data Index: 5675867 (Open Web Text)

Max Activating Token Index: 406

Text #8

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8927. Min Act: -0.1700

Data Index: 7801793 (Open Web Text)

Max Activating Token Index: 84

Text #9

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8273. Min Act: -0.1700

Data Index: 4154582 (Open Web Text)

Max Activating Token Index: 144

Text #10

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8534. Min Act: -0.1700

Data Index: 422380 (Open Web Text)

Max Activating Token Index: 95

Text #11

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8595. Min Act: -0.1700

Data Index: 1865754 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8828. Min Act: -0.1700

Data Index: 2915108 (Open Web Text)

Max Activating Token Index: 324

Text #13

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8026. Min Act: -0.1700

Data Index: 5300285 (Open Web Text)

Max Activating Token Index: 528

Text #14

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8108. Min Act: -0.1700

Data Index: 1009550 (Open Web Text)

Max Activating Token Index: 337

Text #15

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8136. Min Act: -0.1700

Data Index: 8152039 (Open Web Text)

Max Activating Token Index: 179

Text #16

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8311. Min Act: -0.1700

Data Index: 8226123 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8555. Min Act: -0.1700

Data Index: 1980935 (Open Web Text)

Max Activating Token Index: 25

Text #18

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.7825. Min Act: -0.1700

Data Index: 1323869 (Open Web Text)

Max Activating Token Index: 509

Text #19

Max Range: 4.0338. Min Range: -4.0338

Max Act: 3.8284. Min Act: -0.1700

Data Index: 8301859 (Open Web Text)

Max Activating Token Index: 348