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

Dataset: Open Web Text

Neuron 1759 in Layer 4

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: 2.4587. Min Range: -2.4587

Max Act: 2.4468. Min Act: -0.1700

Data Index: 6648219 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.4468. Min Act: -0.1700

Data Index: 3902987 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.4492. Min Act: -0.1700

Data Index: 1465748 (Open Web Text)

Max Activating Token Index: 443

Text #3

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.4587. Min Act: -0.1700

Data Index: 7326595 (Open Web Text)

Max Activating Token Index: 229

Text #4

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.4484. Min Act: -0.1700

Data Index: 2179115 (Open Web Text)

Max Activating Token Index: 148

Text #5

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.4322. Min Act: -0.1700

Data Index: 7229825 (Open Web Text)

Max Activating Token Index: 386

Text #6

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.4168. Min Act: -0.1700

Data Index: 4377691 (Open Web Text)

Max Activating Token Index: 444

Text #7

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.4077. Min Act: -0.1700

Data Index: 5479088 (Open Web Text)

Max Activating Token Index: 206

Text #8

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.4040. Min Act: -0.1700

Data Index: 2892343 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.3825. Min Act: -0.1700

Data Index: 408586 (Open Web Text)

Max Activating Token Index: 100

Text #10

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.4125. Min Act: -0.1700

Data Index: 2414440 (Open Web Text)

Max Activating Token Index: 100

Text #11

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.4017. Min Act: -0.1700

Data Index: 1622616 (Open Web Text)

Max Activating Token Index: 606

Text #12

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.3916. Min Act: -0.1700

Data Index: 7495084 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.3733. Min Act: -0.1700

Data Index: 3897709 (Open Web Text)

Max Activating Token Index: 357

Text #14

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.3538. Min Act: -0.1700

Data Index: 1670088 (Open Web Text)

Max Activating Token Index: 248

Text #15

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.3478. Min Act: -0.1700

Data Index: 7450299 (Open Web Text)

Max Activating Token Index: 956

Text #16

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.3731. Min Act: -0.1700

Data Index: 1940371 (Open Web Text)

Max Activating Token Index: 131

Text #17

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.3458. Min Act: -0.1700

Data Index: 1646679 (Open Web Text)

Max Activating Token Index: 920

Text #18

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.3920. Min Act: -0.1700

Data Index: 3332275 (Open Web Text)

Max Activating Token Index: 499

Text #19

Max Range: 2.4587. Min Range: -2.4587

Max Act: 2.3432. Min Act: -0.1700

Data Index: 2017493 (Open Web Text)

Max Activating Token Index: 142