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

Dataset: Open Web Text

Neuron 1865 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: 4.5046. Min Range: -4.5046

Max Act: 4.5046. Min Act: -0.1700

Data Index: 6532926 (Open Web Text)

Max Activating Token Index: 476

Text #1

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.4560. Min Act: -0.1700

Data Index: 5045606 (Open Web Text)

Max Activating Token Index: 240

Text #2

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.4218. Min Act: -0.1700

Data Index: 2093876 (Open Web Text)

Max Activating Token Index: 925

Text #3

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.4031. Min Act: -0.1700

Data Index: 185593 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.3973. Min Act: -0.1700

Data Index: 7469925 (Open Web Text)

Max Activating Token Index: 273

Text #5

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.4101. Min Act: -0.1700

Data Index: 4698667 (Open Web Text)

Max Activating Token Index: 66

Text #6

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.4162. Min Act: -0.1700

Data Index: 6383869 (Open Web Text)

Max Activating Token Index: 529

Text #7

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.3859. Min Act: -0.1700

Data Index: 1139260 (Open Web Text)

Max Activating Token Index: 194

Text #8

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.4323. Min Act: -0.1700

Data Index: 2219846 (Open Web Text)

Max Activating Token Index: 483

Text #9

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.3885. Min Act: -0.1700

Data Index: 4899492 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.4288. Min Act: -0.1700

Data Index: 2510539 (Open Web Text)

Max Activating Token Index: 573

Text #11

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.3700. Min Act: -0.1700

Data Index: 8291838 (Open Web Text)

Max Activating Token Index: 247

Text #12

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.3566. Min Act: -0.1700

Data Index: 507525 (Open Web Text)

Max Activating Token Index: 911

Text #13

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.3478. Min Act: -0.1700

Data Index: 6968997 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.3704. Min Act: -0.1700

Data Index: 3602302 (Open Web Text)

Max Activating Token Index: 642

Text #15

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.3717. Min Act: -0.1700

Data Index: 3291332 (Open Web Text)

Max Activating Token Index: 142

Text #16

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.3512. Min Act: -0.1700

Data Index: 6775358 (Open Web Text)

Max Activating Token Index: 425

Text #17

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.3320. Min Act: -0.1700

Data Index: 2207822 (Open Web Text)

Max Activating Token Index: 903

Text #18

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.4055. Min Act: -0.1700

Data Index: 801491 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 4.5046. Min Range: -4.5046

Max Act: 4.3536. Min Act: -0.1700

Data Index: 3785690 (Open Web Text)

Max Activating Token Index: 82