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

Dataset: Open Web Text

Neuron 1718 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: 6.7707. Min Range: -6.7707

Max Act: 6.7707. Min Act: -0.1700

Data Index: 7510158 (Open Web Text)

Max Activating Token Index: 296

Text #1

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.4516. Min Act: -0.1700

Data Index: 173117 (Open Web Text)

Max Activating Token Index: 568

Text #2

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.4654. Min Act: -0.1700

Data Index: 311294 (Open Web Text)

Max Activating Token Index: 430

Text #3

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.2187. Min Act: -0.1700

Data Index: 7959787 (Open Web Text)

Max Activating Token Index: 736

Text #4

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.3698. Min Act: -0.1700

Data Index: 6064935 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.3152. Min Act: -0.1700

Data Index: 3457495 (Open Web Text)

Max Activating Token Index: 101

Text #6

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.3277. Min Act: -0.1700

Data Index: 8660259 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.2459. Min Act: -0.1700

Data Index: 4253352 (Open Web Text)

Max Activating Token Index: 218

Text #8

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.2436. Min Act: -0.1700

Data Index: 6425143 (Open Web Text)

Max Activating Token Index: 79

Text #9

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.2240. Min Act: -0.1700

Data Index: 8195763 (Open Web Text)

Max Activating Token Index: 69

Text #10

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.2254. Min Act: -0.1700

Data Index: 1509291 (Open Web Text)

Max Activating Token Index: 788

Text #11

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.2491. Min Act: -0.1700

Data Index: 2612609 (Open Web Text)

Max Activating Token Index: 59

Text #12

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.2142. Min Act: -0.1700

Data Index: 6609911 (Open Web Text)

Max Activating Token Index: 699

Text #13

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.2582. Min Act: -0.1700

Data Index: 8780401 (Open Web Text)

Max Activating Token Index: 791

Text #14

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.1692. Min Act: -0.1700

Data Index: 711957 (Open Web Text)

Max Activating Token Index: 872

Text #15

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.1108. Min Act: -0.1700

Data Index: 588624 (Open Web Text)

Max Activating Token Index: 617

Text #16

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.2066. Min Act: -0.1700

Data Index: 6576349 (Open Web Text)

Max Activating Token Index: 205

Text #17

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.2010. Min Act: -0.1700

Data Index: 1167415 (Open Web Text)

Max Activating Token Index: 246

Text #18

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.1440. Min Act: -0.1700

Data Index: 7889565 (Open Web Text)

Max Activating Token Index: 805

Text #19

Max Range: 6.7707. Min Range: -6.7707

Max Act: 6.1313. Min Act: -0.1700

Data Index: 8141957 (Open Web Text)

Max Activating Token Index: 632