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

Dataset: Open Web Text

Neuron 1594 in Layer 5

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: 5.4867. Min Range: -5.4867

Max Act: 5.4867. Min Act: -0.1700

Data Index: 1952917 (Open Web Text)

Max Activating Token Index: 503

Text #1

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.4763. Min Act: -0.1700

Data Index: 6514579 (Open Web Text)

Max Activating Token Index: 601

Text #2

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.4355. Min Act: -0.1700

Data Index: 1999758 (Open Web Text)

Max Activating Token Index: 1013

Text #3

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.3997. Min Act: -0.1700

Data Index: 1952918 (Open Web Text)

Max Activating Token Index: 571

Text #4

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.3456. Min Act: -0.1700

Data Index: 3284415 (Open Web Text)

Max Activating Token Index: 137

Text #5

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.3194. Min Act: -0.1700

Data Index: 337323 (Open Web Text)

Max Activating Token Index: 97

Text #6

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2659. Min Act: -0.1700

Data Index: 7920044 (Open Web Text)

Max Activating Token Index: 689

Text #7

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2876. Min Act: -0.1700

Data Index: 3143358 (Open Web Text)

Max Activating Token Index: 616

Text #8

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2878. Min Act: -0.1700

Data Index: 3584071 (Open Web Text)

Max Activating Token Index: 452

Text #9

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2786. Min Act: -0.1700

Data Index: 1282675 (Open Web Text)

Max Activating Token Index: 791

Text #10

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2726. Min Act: -0.1700

Data Index: 2386620 (Open Web Text)

Max Activating Token Index: 30

Text #11

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2732. Min Act: -0.1700

Data Index: 5344383 (Open Web Text)

Max Activating Token Index: 799

Text #12

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2569. Min Act: -0.1700

Data Index: 8137240 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2359. Min Act: -0.1700

Data Index: 897458 (Open Web Text)

Max Activating Token Index: 896

Text #14

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2659. Min Act: -0.1700

Data Index: 2573877 (Open Web Text)

Max Activating Token Index: 558

Text #15

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2374. Min Act: -0.1700

Data Index: 4431695 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2368. Min Act: -0.1700

Data Index: 7185720 (Open Web Text)

Max Activating Token Index: 291

Text #17

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2342. Min Act: -0.1700

Data Index: 3147649 (Open Web Text)

Max Activating Token Index: 337

Text #18

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2317. Min Act: -0.1700

Data Index: 5782148 (Open Web Text)

Max Activating Token Index: 360

Text #19

Max Range: 5.4867. Min Range: -5.4867

Max Act: 5.2369. Min Act: -0.1700

Data Index: 3876993 (Open Web Text)

Max Activating Token Index: 711