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

Dataset: Open Web Text

Neuron 338 in Layer 0

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: 3.5302. Min Range: -3.5302

Max Act: 3.5302. Min Act: -0.1700

Data Index: 5113707 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.5178. Min Act: -0.1700

Data Index: 48950 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.5244. Min Act: -0.1700

Data Index: 3831870 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4953. Min Act: -0.1700

Data Index: 2325415 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4410. Min Act: -0.1700

Data Index: 2056682 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4284. Min Act: -0.1700

Data Index: 8061026 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4446. Min Act: -0.1700

Data Index: 4781622 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4451. Min Act: -0.1700

Data Index: 7483323 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4451. Min Act: -0.1700

Data Index: 2195218 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4345. Min Act: -0.1700

Data Index: 1198583 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4196. Min Act: -0.1700

Data Index: 3684457 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4195. Min Act: -0.1700

Data Index: 2273352 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4084. Min Act: -0.1700

Data Index: 3684518 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4000. Min Act: -0.1700

Data Index: 6906548 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4007. Min Act: -0.1700

Data Index: 4347870 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4045. Min Act: -0.1700

Data Index: 7814815 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3998. Min Act: -0.1700

Data Index: 746875 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3984. Min Act: -0.1700

Data Index: 6859630 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4089. Min Act: -0.1700

Data Index: 450926 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4121. Min Act: -0.1700

Data Index: 5940015 (Open Web Text)

Max Activating Token Index: 3