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

Dataset: Open Web Text

Neuron 1729 in Layer 6

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: 4.0785. Min Range: -4.0785

Max Act: 4.0785. Min Act: -0.1700

Data Index: 2088720 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.9473. Min Act: -0.1700

Data Index: 2902274 (Open Web Text)

Max Activating Token Index: 944

Text #2

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.9297. Min Act: -0.1700

Data Index: 5489232 (Open Web Text)

Max Activating Token Index: 259

Text #3

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.8804. Min Act: -0.1700

Data Index: 1701799 (Open Web Text)

Max Activating Token Index: 567

Text #4

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.8542. Min Act: -0.1700

Data Index: 3824172 (Open Web Text)

Max Activating Token Index: 243

Text #5

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.8535. Min Act: -0.1700

Data Index: 2478733 (Open Web Text)

Max Activating Token Index: 698

Text #6

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.8245. Min Act: -0.1700

Data Index: 478461 (Open Web Text)

Max Activating Token Index: 1017

Text #7

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.8401. Min Act: -0.1700

Data Index: 2577629 (Open Web Text)

Max Activating Token Index: 79

Text #8

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.8343. Min Act: -0.1700

Data Index: 6187324 (Open Web Text)

Max Activating Token Index: 749

Text #9

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.8250. Min Act: -0.1700

Data Index: 1328921 (Open Web Text)

Max Activating Token Index: 211

Text #10

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.8294. Min Act: -0.1700

Data Index: 3537242 (Open Web Text)

Max Activating Token Index: 49

Text #11

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.7998. Min Act: -0.1700

Data Index: 1438658 (Open Web Text)

Max Activating Token Index: 116

Text #12

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.8209. Min Act: -0.1700

Data Index: 1277148 (Open Web Text)

Max Activating Token Index: 959

Text #13

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.7956. Min Act: -0.1700

Data Index: 4817325 (Open Web Text)

Max Activating Token Index: 650

Text #14

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.8154. Min Act: -0.1700

Data Index: 1456524 (Open Web Text)

Max Activating Token Index: 473

Text #15

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.8058. Min Act: -0.1700

Data Index: 7307395 (Open Web Text)

Max Activating Token Index: 236

Text #16

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.7890. Min Act: -0.1700

Data Index: 7545504 (Open Web Text)

Max Activating Token Index: 435

Text #17

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.7408. Min Act: -0.1700

Data Index: 7512412 (Open Web Text)

Max Activating Token Index: 624

Text #18

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.7838. Min Act: -0.1700

Data Index: 959792 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.7770. Min Act: -0.1700

Data Index: 5488517 (Open Web Text)

Max Activating Token Index: 98