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

Dataset: Open Web Text

Neuron 2895 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: 3.7307. Min Range: -3.7307

Max Act: 3.7307. Min Act: -0.1700

Data Index: 2400525 (Open Web Text)

Max Activating Token Index: 307

Text #1

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.6700. Min Act: -0.1700

Data Index: 5695339 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.6269. Min Act: -0.1700

Data Index: 1732042 (Open Web Text)

Max Activating Token Index: 718

Text #3

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.6563. Min Act: -0.1700

Data Index: 786496 (Open Web Text)

Max Activating Token Index: 963

Text #4

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.6240. Min Act: -0.1700

Data Index: 1748195 (Open Web Text)

Max Activating Token Index: 492

Text #5

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.6148. Min Act: -0.1700

Data Index: 7727342 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5830. Min Act: -0.1700

Data Index: 3847905 (Open Web Text)

Max Activating Token Index: 737

Text #7

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5850. Min Act: -0.1700

Data Index: 1570027 (Open Web Text)

Max Activating Token Index: 407

Text #8

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5920. Min Act: -0.1700

Data Index: 8754768 (Open Web Text)

Max Activating Token Index: 642

Text #9

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5804. Min Act: -0.1700

Data Index: 6363383 (Open Web Text)

Max Activating Token Index: 52

Text #10

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5768. Min Act: -0.1700

Data Index: 4515205 (Open Web Text)

Max Activating Token Index: 609

Text #11

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5778. Min Act: -0.1700

Data Index: 7713935 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5708. Min Act: -0.1700

Data Index: 3797972 (Open Web Text)

Max Activating Token Index: 81

Text #13

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5501. Min Act: -0.1700

Data Index: 8492435 (Open Web Text)

Max Activating Token Index: 145

Text #14

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5319. Min Act: -0.1700

Data Index: 943078 (Open Web Text)

Max Activating Token Index: 293

Text #15

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5210. Min Act: -0.1700

Data Index: 8027372 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5268. Min Act: -0.1700

Data Index: 5778366 (Open Web Text)

Max Activating Token Index: 310

Text #17

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.4787. Min Act: -0.1700

Data Index: 5607325 (Open Web Text)

Max Activating Token Index: 800

Text #18

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.5069. Min Act: -0.1700

Data Index: 5631974 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 3.7307. Min Range: -3.7307

Max Act: 3.4644. Min Act: -0.1700

Data Index: 5805158 (Open Web Text)

Max Activating Token Index: 975