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

Dataset: Open Web Text

Neuron 954 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: 4.5108. Min Range: -4.5108

Max Act: 4.5108. Min Act: -0.1700

Data Index: 4825587 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.5046. Min Act: -0.1700

Data Index: 6611671 (Open Web Text)

Max Activating Token Index: 978

Text #2

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.4603. Min Act: -0.1700

Data Index: 7967119 (Open Web Text)

Max Activating Token Index: 248

Text #3

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.4412. Min Act: -0.1700

Data Index: 4648184 (Open Web Text)

Max Activating Token Index: 232

Text #4

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.4414. Min Act: -0.1700

Data Index: 3945654 (Open Web Text)

Max Activating Token Index: 548

Text #5

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.4228. Min Act: -0.1700

Data Index: 2201756 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.3950. Min Act: -0.1700

Data Index: 8251570 (Open Web Text)

Max Activating Token Index: 810

Text #7

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.4767. Min Act: -0.1700

Data Index: 1245032 (Open Web Text)

Max Activating Token Index: 517

Text #8

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.3910. Min Act: -0.1700

Data Index: 6000715 (Open Web Text)

Max Activating Token Index: 303

Text #9

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.3216. Min Act: -0.1700

Data Index: 1980515 (Open Web Text)

Max Activating Token Index: 820

Text #10

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.3298. Min Act: -0.1700

Data Index: 5876706 (Open Web Text)

Max Activating Token Index: 687

Text #11

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.3315. Min Act: -0.1700

Data Index: 937199 (Open Web Text)

Max Activating Token Index: 824

Text #12

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.3683. Min Act: -0.1700

Data Index: 7708704 (Open Web Text)

Max Activating Token Index: 151

Text #13

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.2951. Min Act: -0.1700

Data Index: 6747330 (Open Web Text)

Max Activating Token Index: 60

Text #14

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.3297. Min Act: -0.1700

Data Index: 4648183 (Open Web Text)

Max Activating Token Index: 557

Text #15

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.2810. Min Act: -0.1700

Data Index: 6612844 (Open Web Text)

Max Activating Token Index: 523

Text #16

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.2761. Min Act: -0.1700

Data Index: 8151056 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.2456. Min Act: -0.1700

Data Index: 5450598 (Open Web Text)

Max Activating Token Index: 652

Text #18

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.2797. Min Act: -0.1700

Data Index: 5110263 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.2133. Min Act: -0.1700

Data Index: 6016325 (Open Web Text)

Max Activating Token Index: 493