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

Dataset: Open Web Text

Neuron 2834 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: 4.5154. Min Range: -4.5154

Max Act: 4.5154. Min Act: -0.1700

Data Index: 8035760 (Open Web Text)

Max Activating Token Index: 640

Text #1

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.4397. Min Act: -0.1700

Data Index: 1144343 (Open Web Text)

Max Activating Token Index: 605

Text #2

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.3374. Min Act: -0.1700

Data Index: 677331 (Open Web Text)

Max Activating Token Index: 419

Text #3

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.3027. Min Act: -0.1699

Data Index: 5534162 (Open Web Text)

Max Activating Token Index: 649

Text #4

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2966. Min Act: -0.1700

Data Index: 321005 (Open Web Text)

Max Activating Token Index: 258

Text #5

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2908. Min Act: -0.1700

Data Index: 162937 (Open Web Text)

Max Activating Token Index: 420

Text #6

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2624. Min Act: -0.1700

Data Index: 2553807 (Open Web Text)

Max Activating Token Index: 327

Text #7

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2410. Min Act: -0.1700

Data Index: 3458432 (Open Web Text)

Max Activating Token Index: 426

Text #8

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2523. Min Act: -0.1700

Data Index: 6531107 (Open Web Text)

Max Activating Token Index: 671

Text #9

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2626. Min Act: -0.1700

Data Index: 3830475 (Open Web Text)

Max Activating Token Index: 618

Text #10

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2465. Min Act: -0.1700

Data Index: 174797 (Open Web Text)

Max Activating Token Index: 884

Text #11

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2768. Min Act: -0.1700

Data Index: 8604823 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2279. Min Act: -0.1700

Data Index: 5366343 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2331. Min Act: -0.1700

Data Index: 2729962 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2324. Min Act: -0.1700

Data Index: 1928665 (Open Web Text)

Max Activating Token Index: 447

Text #15

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2509. Min Act: -0.1700

Data Index: 8630324 (Open Web Text)

Max Activating Token Index: 279

Text #16

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.1771. Min Act: -0.1700

Data Index: 462719 (Open Web Text)

Max Activating Token Index: 567

Text #17

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2286. Min Act: -0.1700

Data Index: 4340542 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.1928. Min Act: -0.1700

Data Index: 7995142 (Open Web Text)

Max Activating Token Index: 325

Text #19

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.1828. Min Act: -0.1700

Data Index: 4790700 (Open Web Text)

Max Activating Token Index: 376