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

Dataset: Open Web Text

Neuron 878 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: 4.7594. Min Range: -4.7594

Max Act: 4.7594. Min Act: -0.1700

Data Index: 5099130 (Open Web Text)

Max Activating Token Index: 167

Text #1

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.4717. Min Act: -0.1700

Data Index: 5099520 (Open Web Text)

Max Activating Token Index: 332

Text #2

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.4323. Min Act: -0.1700

Data Index: 8811316 (Open Web Text)

Max Activating Token Index: 360

Text #3

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.4016. Min Act: -0.1700

Data Index: 5499851 (Open Web Text)

Max Activating Token Index: 815

Text #4

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.4341. Min Act: -0.1700

Data Index: 2115871 (Open Web Text)

Max Activating Token Index: 943

Text #5

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.4096. Min Act: -0.1700

Data Index: 3457136 (Open Web Text)

Max Activating Token Index: 218

Text #6

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.3658. Min Act: -0.1700

Data Index: 5765501 (Open Web Text)

Max Activating Token Index: 613

Text #7

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.3745. Min Act: -0.1700

Data Index: 1135178 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.3715. Min Act: -0.1700

Data Index: 5272417 (Open Web Text)

Max Activating Token Index: 137

Text #9

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.3161. Min Act: -0.1700

Data Index: 3667598 (Open Web Text)

Max Activating Token Index: 490

Text #10

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.3393. Min Act: -0.1700

Data Index: 1808632 (Open Web Text)

Max Activating Token Index: 908

Text #11

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.3431. Min Act: -0.1700

Data Index: 5920082 (Open Web Text)

Max Activating Token Index: 752

Text #12

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.3488. Min Act: -0.1700

Data Index: 1353300 (Open Web Text)

Max Activating Token Index: 451

Text #13

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.2943. Min Act: -0.1700

Data Index: 926176 (Open Web Text)

Max Activating Token Index: 803

Text #14

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.2864. Min Act: -0.1700

Data Index: 1670095 (Open Web Text)

Max Activating Token Index: 201

Text #15

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.3187. Min Act: -0.1700

Data Index: 5889716 (Open Web Text)

Max Activating Token Index: 419

Text #16

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.2810. Min Act: -0.1700

Data Index: 1696444 (Open Web Text)

Max Activating Token Index: 643

Text #17

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.3160. Min Act: -0.1700

Data Index: 7465863 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.2440. Min Act: -0.1700

Data Index: 8390791 (Open Web Text)

Max Activating Token Index: 933

Text #19

Max Range: 4.7594. Min Range: -4.7594

Max Act: 4.2601. Min Act: -0.1700

Data Index: 805273 (Open Web Text)

Max Activating Token Index: 665