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

Dataset: Open Web Text

Neuron 2123 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: 1.3644. Min Range: -1.3644

Max Act: 1.3644. Min Act: -0.1700

Data Index: 4474499 (Open Web Text)

Max Activating Token Index: 231

Text #1

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3552. Min Act: -0.1700

Data Index: 907682 (Open Web Text)

Max Activating Token Index: 301

Text #2

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3489. Min Act: -0.1700

Data Index: 1421947 (Open Web Text)

Max Activating Token Index: 995

Text #3

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3370. Min Act: -0.1700

Data Index: 1598414 (Open Web Text)

Max Activating Token Index: 120

Text #4

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3261. Min Act: -0.1700

Data Index: 980153 (Open Web Text)

Max Activating Token Index: 418

Text #5

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3256. Min Act: -0.1700

Data Index: 8256546 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3232. Min Act: -0.1699

Data Index: 6016302 (Open Web Text)

Max Activating Token Index: 562

Text #7

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3123. Min Act: -0.1700

Data Index: 6010443 (Open Web Text)

Max Activating Token Index: 487

Text #8

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3175. Min Act: -0.1699

Data Index: 3517898 (Open Web Text)

Max Activating Token Index: 968

Text #9

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3126. Min Act: -0.1700

Data Index: 1830557 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3171. Min Act: -0.1700

Data Index: 1810097 (Open Web Text)

Max Activating Token Index: 620

Text #11

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3154. Min Act: -0.1700

Data Index: 2961188 (Open Web Text)

Max Activating Token Index: 563

Text #12

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3099. Min Act: -0.1700

Data Index: 1571512 (Open Web Text)

Max Activating Token Index: 976

Text #13

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3202. Min Act: -0.1698

Data Index: 3946533 (Open Web Text)

Max Activating Token Index: 1009

Text #14

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3031. Min Act: -0.1700

Data Index: 740006 (Open Web Text)

Max Activating Token Index: 551

Text #15

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3069. Min Act: -0.1700

Data Index: 6797414 (Open Web Text)

Max Activating Token Index: 123

Text #16

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3067. Min Act: -0.1700

Data Index: 5205138 (Open Web Text)

Max Activating Token Index: 71

Text #17

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3007. Min Act: -0.1700

Data Index: 8132957 (Open Web Text)

Max Activating Token Index: 560

Text #18

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3028. Min Act: -0.1700

Data Index: 6335594 (Open Web Text)

Max Activating Token Index: 620

Text #19

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3000. Min Act: -0.1700

Data Index: 3551362 (Open Web Text)

Max Activating Token Index: 713