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

Dataset: Open Web Text

Neuron 2515 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: 3.5368. Min Range: -3.5368

Max Act: 3.5368. Min Act: -0.1700

Data Index: 4162724 (Open Web Text)

Max Activating Token Index: 377

Text #1

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4942. Min Act: -0.1700

Data Index: 1328034 (Open Web Text)

Max Activating Token Index: 153

Text #2

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4763. Min Act: -0.1700

Data Index: 6744909 (Open Web Text)

Max Activating Token Index: 734

Text #3

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4489. Min Act: -0.1700

Data Index: 8019578 (Open Web Text)

Max Activating Token Index: 205

Text #4

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4448. Min Act: -0.1700

Data Index: 6197336 (Open Web Text)

Max Activating Token Index: 335

Text #5

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4433. Min Act: -0.1700

Data Index: 7712998 (Open Web Text)

Max Activating Token Index: 635

Text #6

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4198. Min Act: -0.1700

Data Index: 6187686 (Open Web Text)

Max Activating Token Index: 146

Text #7

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4325. Min Act: -0.1700

Data Index: 4142633 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4340. Min Act: -0.1700

Data Index: 692225 (Open Web Text)

Max Activating Token Index: 421

Text #9

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1443690 (Open Web Text)

Max Activating Token Index: 827

Text #10

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4192. Min Act: -0.1700

Data Index: 2665951 (Open Web Text)

Max Activating Token Index: 891

Text #11

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4045. Min Act: -0.1700

Data Index: 205527 (Open Web Text)

Max Activating Token Index: 377

Text #12

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4074. Min Act: -0.1700

Data Index: 10416 (Open Web Text)

Max Activating Token Index: 614

Text #13

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.4074. Min Act: -0.1700

Data Index: 1805620 (Open Web Text)

Max Activating Token Index: 565

Text #14

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.3971. Min Act: -0.1700

Data Index: 6769971 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.3761. Min Act: -0.1700

Data Index: 1077089 (Open Web Text)

Max Activating Token Index: 141

Text #16

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.3918. Min Act: -0.1700

Data Index: 3474090 (Open Web Text)

Max Activating Token Index: 160

Text #17

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.3895. Min Act: -0.1700

Data Index: 5489939 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.3831. Min Act: -0.1700

Data Index: 794267 (Open Web Text)

Max Activating Token Index: 345

Text #19

Max Range: 3.5368. Min Range: -3.5368

Max Act: 3.3673. Min Act: -0.1700

Data Index: 4454959 (Open Web Text)

Max Activating Token Index: 812