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

Dataset: Open Web Text

Neuron 2397 in Layer 6

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: 5.0693. Min Range: -5.0693

Max Act: 5.0693. Min Act: -0.1700

Data Index: 4359836 (Open Web Text)

Max Activating Token Index: 185

Text #1

Max Range: 5.0693. Min Range: -5.0693

Max Act: 5.0358. Min Act: -0.1700

Data Index: 518560 (Open Web Text)

Max Activating Token Index: 531

Text #2

Max Range: 5.0693. Min Range: -5.0693

Max Act: 5.0341. Min Act: -0.1700

Data Index: 4479908 (Open Web Text)

Max Activating Token Index: 184

Text #3

Max Range: 5.0693. Min Range: -5.0693

Max Act: 5.0043. Min Act: -0.1700

Data Index: 5242059 (Open Web Text)

Max Activating Token Index: 358

Text #4

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.9399. Min Act: -0.1700

Data Index: 1756276 (Open Web Text)

Max Activating Token Index: 257

Text #5

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.9148. Min Act: -0.1700

Data Index: 2932985 (Open Web Text)

Max Activating Token Index: 86

Text #6

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.9300. Min Act: -0.1700

Data Index: 6180880 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.9105. Min Act: -0.1700

Data Index: 8275524 (Open Web Text)

Max Activating Token Index: 840

Text #8

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.8779. Min Act: -0.1700

Data Index: 4793280 (Open Web Text)

Max Activating Token Index: 93

Text #9

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.9066. Min Act: -0.1700

Data Index: 6977687 (Open Web Text)

Max Activating Token Index: 102

Text #10

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.8751. Min Act: -0.1700

Data Index: 8275525 (Open Web Text)

Max Activating Token Index: 349

Text #11

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.8677. Min Act: -0.1700

Data Index: 7529895 (Open Web Text)

Max Activating Token Index: 196

Text #12

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.8656. Min Act: -0.1700

Data Index: 5339876 (Open Web Text)

Max Activating Token Index: 268

Text #13

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.8573. Min Act: -0.1700

Data Index: 2567397 (Open Web Text)

Max Activating Token Index: 142

Text #14

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.8764. Min Act: -0.1700

Data Index: 1202184 (Open Web Text)

Max Activating Token Index: 87

Text #15

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.8775. Min Act: -0.1700

Data Index: 1221505 (Open Web Text)

Max Activating Token Index: 69

Text #16

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.8410. Min Act: -0.1700

Data Index: 669497 (Open Web Text)

Max Activating Token Index: 727

Text #17

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.8665. Min Act: -0.1700

Data Index: 3147304 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.8437. Min Act: -0.1700

Data Index: 1917787 (Open Web Text)

Max Activating Token Index: 292

Text #19

Max Range: 5.0693. Min Range: -5.0693

Max Act: 4.8391. Min Act: -0.1700

Data Index: 1565267 (Open Web Text)

Max Activating Token Index: 142