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

Dataset: Open Web Text

Neuron 2724 in Layer 1

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: 1.6970. Min Range: -1.6970

Max Act: 1.6970. Min Act: -0.1700

Data Index: 5733977 (Open Web Text)

Max Activating Token Index: 520

Text #1

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6821. Min Act: -0.1700

Data Index: 4803235 (Open Web Text)

Max Activating Token Index: 189

Text #2

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6790. Min Act: -0.1700

Data Index: 5567452 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6577. Min Act: -0.1700

Data Index: 4035713 (Open Web Text)

Max Activating Token Index: 798

Text #4

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6534. Min Act: -0.1700

Data Index: 5193878 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6472. Min Act: -0.1700

Data Index: 3495939 (Open Web Text)

Max Activating Token Index: 423

Text #6

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6451. Min Act: -0.1700

Data Index: 5965162 (Open Web Text)

Max Activating Token Index: 473

Text #7

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6524. Min Act: -0.1700

Data Index: 6410081 (Open Web Text)

Max Activating Token Index: 998

Text #8

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6417. Min Act: -0.1700

Data Index: 5435992 (Open Web Text)

Max Activating Token Index: 57

Text #9

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6362. Min Act: -0.1700

Data Index: 4959339 (Open Web Text)

Max Activating Token Index: 148

Text #10

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6297. Min Act: -0.1700

Data Index: 2674454 (Open Web Text)

Max Activating Token Index: 276

Text #11

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6297. Min Act: -0.1700

Data Index: 3740692 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6324. Min Act: -0.1700

Data Index: 7232080 (Open Web Text)

Max Activating Token Index: 577

Text #13

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6176. Min Act: -0.1700

Data Index: 1145941 (Open Web Text)

Max Activating Token Index: 534

Text #14

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6220. Min Act: -0.1700

Data Index: 473893 (Open Web Text)

Max Activating Token Index: 705

Text #15

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6153. Min Act: -0.1700

Data Index: 5966351 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6050. Min Act: -0.1699

Data Index: 4431144 (Open Web Text)

Max Activating Token Index: 878

Text #17

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.5985. Min Act: -0.1699

Data Index: 103357 (Open Web Text)

Max Activating Token Index: 983

Text #18

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6096. Min Act: -0.1700

Data Index: 6516923 (Open Web Text)

Max Activating Token Index: 704

Text #19

Max Range: 1.6970. Min Range: -1.6970

Max Act: 1.6113. Min Act: -0.1700

Data Index: 872368 (Open Web Text)

Max Activating Token Index: 958