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

Dataset: Open Web Text

Neuron 468 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: 4.1939. Min Range: -4.1939

Max Act: 4.1939. Min Act: -0.1700

Data Index: 4423690 (Open Web Text)

Max Activating Token Index: 35

Text #1

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.1125. Min Act: -0.1700

Data Index: 170163 (Open Web Text)

Max Activating Token Index: 421

Text #2

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.1341. Min Act: -0.1700

Data Index: 1838104 (Open Web Text)

Max Activating Token Index: 736

Text #3

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0778. Min Act: -0.1700

Data Index: 6049564 (Open Web Text)

Max Activating Token Index: 948

Text #4

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0676. Min Act: -0.1700

Data Index: 8093163 (Open Web Text)

Max Activating Token Index: 588

Text #5

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0822. Min Act: -0.1700

Data Index: 4548207 (Open Web Text)

Max Activating Token Index: 327

Text #6

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0468. Min Act: -0.1700

Data Index: 4663213 (Open Web Text)

Max Activating Token Index: 468

Text #7

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0439. Min Act: -0.1700

Data Index: 2609515 (Open Web Text)

Max Activating Token Index: 133

Text #8

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0449. Min Act: -0.1700

Data Index: 5836255 (Open Web Text)

Max Activating Token Index: 756

Text #9

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0799. Min Act: -0.1700

Data Index: 4327032 (Open Web Text)

Max Activating Token Index: 426

Text #10

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0718. Min Act: -0.1700

Data Index: 156563 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0505. Min Act: -0.1700

Data Index: 2805235 (Open Web Text)

Max Activating Token Index: 262

Text #12

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0043. Min Act: -0.1700

Data Index: 2437139 (Open Web Text)

Max Activating Token Index: 463

Text #13

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0387. Min Act: -0.1700

Data Index: 4665720 (Open Web Text)

Max Activating Token Index: 998

Text #14

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0520. Min Act: -0.1700

Data Index: 2985901 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0400. Min Act: -0.1700

Data Index: 5780711 (Open Web Text)

Max Activating Token Index: 114

Text #16

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0129. Min Act: -0.1700

Data Index: 4711977 (Open Web Text)

Max Activating Token Index: 773

Text #17

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0247. Min Act: -0.1700

Data Index: 4444011 (Open Web Text)

Max Activating Token Index: 846

Text #18

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.9952. Min Act: -0.1700

Data Index: 356789 (Open Web Text)

Max Activating Token Index: 964

Text #19

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.9994. Min Act: -0.1700

Data Index: 1019146 (Open Web Text)

Max Activating Token Index: 413