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

Dataset: Open Web Text

Neuron 358 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: 4.5280. Min Range: -4.5280

Max Act: 4.5280. Min Act: -0.1700

Data Index: 4072429 (Open Web Text)

Max Activating Token Index: 92

Text #1

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.4970. Min Act: -0.1700

Data Index: 3934179 (Open Web Text)

Max Activating Token Index: 763

Text #2

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.4245. Min Act: -0.1700

Data Index: 5343312 (Open Web Text)

Max Activating Token Index: 322

Text #3

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.3898. Min Act: -0.1700

Data Index: 5982943 (Open Web Text)

Max Activating Token Index: 254

Text #4

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.4038. Min Act: -0.1700

Data Index: 4936142 (Open Web Text)

Max Activating Token Index: 703

Text #5

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.3652. Min Act: -0.1700

Data Index: 3596463 (Open Web Text)

Max Activating Token Index: 397

Text #6

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.3838. Min Act: -0.1700

Data Index: 2639344 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.3679. Min Act: -0.1700

Data Index: 7468359 (Open Web Text)

Max Activating Token Index: 467

Text #8

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.3342. Min Act: -0.1700

Data Index: 5982942 (Open Web Text)

Max Activating Token Index: 578

Text #9

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.3349. Min Act: -0.1700

Data Index: 6764935 (Open Web Text)

Max Activating Token Index: 374

Text #10

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.3233. Min Act: -0.1700

Data Index: 7564512 (Open Web Text)

Max Activating Token Index: 604

Text #11

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.2723. Min Act: -0.1700

Data Index: 5982941 (Open Web Text)

Max Activating Token Index: 823

Text #12

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.3013. Min Act: -0.1700

Data Index: 7102381 (Open Web Text)

Max Activating Token Index: 499

Text #13

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.2915. Min Act: -0.1700

Data Index: 133041 (Open Web Text)

Max Activating Token Index: 692

Text #14

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.2303. Min Act: -0.1700

Data Index: 6523031 (Open Web Text)

Max Activating Token Index: 125

Text #15

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.2476. Min Act: -0.1700

Data Index: 7258321 (Open Web Text)

Max Activating Token Index: 899

Text #16

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.2373. Min Act: -0.1700

Data Index: 4294300 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.2305. Min Act: -0.1700

Data Index: 133042 (Open Web Text)

Max Activating Token Index: 993

Text #18

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.1881. Min Act: -0.1700

Data Index: 71191 (Open Web Text)

Max Activating Token Index: 26

Text #19

Max Range: 4.5280. Min Range: -4.5280

Max Act: 4.2183. Min Act: -0.1700

Data Index: 5607881 (Open Web Text)

Max Activating Token Index: 570