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

Dataset: Open Web Text

Neuron 1359 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: 3.5113. Min Range: -3.5113

Max Act: 3.5113. Min Act: -0.1700

Data Index: 3576584 (Open Web Text)

Max Activating Token Index: 855

Text #1

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4870. Min Act: -0.1700

Data Index: 256851 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4732. Min Act: -0.1700

Data Index: 8083762 (Open Web Text)

Max Activating Token Index: 272

Text #3

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4603. Min Act: -0.1700

Data Index: 7902730 (Open Web Text)

Max Activating Token Index: 692

Text #4

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4554. Min Act: -0.1700

Data Index: 2804493 (Open Web Text)

Max Activating Token Index: 263

Text #5

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4444. Min Act: -0.1700

Data Index: 5263874 (Open Web Text)

Max Activating Token Index: 371

Text #6

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4539. Min Act: -0.1700

Data Index: 1715315 (Open Web Text)

Max Activating Token Index: 689

Text #7

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4361. Min Act: -0.1700

Data Index: 8513024 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4425. Min Act: -0.1700

Data Index: 6986102 (Open Web Text)

Max Activating Token Index: 243

Text #9

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4465. Min Act: -0.1700

Data Index: 8191660 (Open Web Text)

Max Activating Token Index: 244

Text #10

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4159. Min Act: -0.1700

Data Index: 8394897 (Open Web Text)

Max Activating Token Index: 677

Text #11

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4121. Min Act: -0.1700

Data Index: 2004885 (Open Web Text)

Max Activating Token Index: 225

Text #12

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4031. Min Act: -0.1700

Data Index: 2916493 (Open Web Text)

Max Activating Token Index: 504

Text #13

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.3999. Min Act: -0.1700

Data Index: 2412057 (Open Web Text)

Max Activating Token Index: 884

Text #14

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.4134. Min Act: -0.1700

Data Index: 4862160 (Open Web Text)

Max Activating Token Index: 169

Text #15

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.3710. Min Act: -0.1700

Data Index: 2757178 (Open Web Text)

Max Activating Token Index: 258

Text #16

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.3929. Min Act: -0.1700

Data Index: 1278489 (Open Web Text)

Max Activating Token Index: 798

Text #17

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.3555. Min Act: -0.1700

Data Index: 7313078 (Open Web Text)

Max Activating Token Index: 129

Text #18

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.3904. Min Act: -0.1700

Data Index: 4997127 (Open Web Text)

Max Activating Token Index: 329

Text #19

Max Range: 3.5113. Min Range: -3.5113

Max Act: 3.3840. Min Act: -0.1700

Data Index: 1375956 (Open Web Text)

Max Activating Token Index: 49