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

Dataset: Open Web Text

Neuron 127 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: 3.4612. Min Range: -3.4612

Max Act: 3.4612. Min Act: -0.1700

Data Index: 5045927 (Open Web Text)

Max Activating Token Index: 587

Text #1

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.4378. Min Act: -0.1700

Data Index: 2584893 (Open Web Text)

Max Activating Token Index: 340

Text #2

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3753. Min Act: -0.1700

Data Index: 340055 (Open Web Text)

Max Activating Token Index: 106

Text #3

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.2933. Min Act: -0.1700

Data Index: 3600426 (Open Web Text)

Max Activating Token Index: 285

Text #4

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3133. Min Act: -0.1700

Data Index: 574838 (Open Web Text)

Max Activating Token Index: 389

Text #5

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.2748. Min Act: -0.1700

Data Index: 7309960 (Open Web Text)

Max Activating Token Index: 517

Text #6

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.2810. Min Act: -0.1700

Data Index: 7858552 (Open Web Text)

Max Activating Token Index: 103

Text #7

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.2648. Min Act: -0.1700

Data Index: 3205829 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.2197. Min Act: -0.1700

Data Index: 3874046 (Open Web Text)

Max Activating Token Index: 797

Text #9

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.2174. Min Act: -0.1700

Data Index: 8357467 (Open Web Text)

Max Activating Token Index: 97

Text #10

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.2423. Min Act: -0.1700

Data Index: 7585348 (Open Web Text)

Max Activating Token Index: 410

Text #11

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.2250. Min Act: -0.1700

Data Index: 8164350 (Open Web Text)

Max Activating Token Index: 1001

Text #12

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.1993. Min Act: -0.1700

Data Index: 3308682 (Open Web Text)

Max Activating Token Index: 420

Text #13

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.2324. Min Act: -0.1700

Data Index: 4822923 (Open Web Text)

Max Activating Token Index: 820

Text #14

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.1997. Min Act: -0.1700

Data Index: 8134379 (Open Web Text)

Max Activating Token Index: 673

Text #15

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.1956. Min Act: -0.1700

Data Index: 3430044 (Open Web Text)

Max Activating Token Index: 689

Text #16

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.1744. Min Act: -0.1700

Data Index: 3118513 (Open Web Text)

Max Activating Token Index: 238

Text #17

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.1770. Min Act: -0.1700

Data Index: 3757958 (Open Web Text)

Max Activating Token Index: 170

Text #18

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.1418. Min Act: -0.1700

Data Index: 5930053 (Open Web Text)

Max Activating Token Index: 218

Text #19

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.1614. Min Act: -0.1700

Data Index: 4362507 (Open Web Text)

Max Activating Token Index: 875