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

Dataset: Open Web Text

Neuron 178 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: 3.4538. Min Range: -3.4538

Max Act: 3.3702. Min Act: -0.1700

Data Index: 7602476 (Open Web Text)

Max Activating Token Index: 119

Text #1

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.4538. Min Act: -0.1700

Data Index: 5707237 (Open Web Text)

Max Activating Token Index: 666

Text #2

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.3475. Min Act: -0.1700

Data Index: 6992418 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2694. Min Act: -0.1700

Data Index: 5568953 (Open Web Text)

Max Activating Token Index: 825

Text #4

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.3265. Min Act: -0.1700

Data Index: 5801925 (Open Web Text)

Max Activating Token Index: 323

Text #5

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.3200. Min Act: -0.1700

Data Index: 2396674 (Open Web Text)

Max Activating Token Index: 365

Text #6

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.3019. Min Act: -0.1700

Data Index: 4887715 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.3022. Min Act: -0.1700

Data Index: 3396672 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2547. Min Act: -0.1700

Data Index: 4909296 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2609. Min Act: -0.1700

Data Index: 6375862 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2554. Min Act: -0.1700

Data Index: 3915075 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2366. Min Act: -0.1700

Data Index: 131308 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2560. Min Act: -0.1700

Data Index: 4909343 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2278. Min Act: -0.1700

Data Index: 8544083 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.1983. Min Act: -0.1700

Data Index: 5481104 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2120. Min Act: -0.1700

Data Index: 7116629 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2105. Min Act: -0.1700

Data Index: 4791010 (Open Web Text)

Max Activating Token Index: 290

Text #17

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.1736. Min Act: -0.1700

Data Index: 7602483 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.1907. Min Act: -0.1700

Data Index: 1198285 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.4538. Min Range: -3.4538

Max Act: 3.2144. Min Act: -0.1700

Data Index: 7287732 (Open Web Text)

Max Activating Token Index: 103