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

Dataset: Open Web Text

Neuron 2394 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: 4.3810. Min Range: -4.3810

Max Act: 4.3810. Min Act: -0.1700

Data Index: 92109 (Open Web Text)

Max Activating Token Index: 909

Text #1

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.3293. Min Act: -0.1700

Data Index: 6527818 (Open Web Text)

Max Activating Token Index: 340

Text #2

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.3579. Min Act: -0.1700

Data Index: 1956431 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.2382. Min Act: -0.1700

Data Index: 6172092 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.2654. Min Act: -0.1700

Data Index: 4513239 (Open Web Text)

Max Activating Token Index: 906

Text #5

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.1986. Min Act: -0.1700

Data Index: 7092294 (Open Web Text)

Max Activating Token Index: 585

Text #6

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.2299. Min Act: -0.1700

Data Index: 3924654 (Open Web Text)

Max Activating Token Index: 287

Text #7

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.2087. Min Act: -0.1700

Data Index: 1523453 (Open Web Text)

Max Activating Token Index: 278

Text #8

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.2352. Min Act: -0.1700

Data Index: 8723758 (Open Web Text)

Max Activating Token Index: 839

Text #9

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.2021. Min Act: -0.1700

Data Index: 3500201 (Open Web Text)

Max Activating Token Index: 500

Text #10

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.2014. Min Act: -0.1700

Data Index: 7040257 (Open Web Text)

Max Activating Token Index: 877

Text #11

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.1831. Min Act: -0.1700

Data Index: 2330758 (Open Web Text)

Max Activating Token Index: 176

Text #12

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.1919. Min Act: -0.1700

Data Index: 7613533 (Open Web Text)

Max Activating Token Index: 568

Text #13

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.2173. Min Act: -0.1700

Data Index: 7167553 (Open Web Text)

Max Activating Token Index: 171

Text #14

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.1946. Min Act: -0.1700

Data Index: 7133705 (Open Web Text)

Max Activating Token Index: 159

Text #15

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.2780. Min Act: -0.1700

Data Index: 7109767 (Open Web Text)

Max Activating Token Index: 312

Text #16

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.1669. Min Act: -0.1700

Data Index: 4447422 (Open Web Text)

Max Activating Token Index: 793

Text #17

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.1862. Min Act: -0.1700

Data Index: 7860430 (Open Web Text)

Max Activating Token Index: 418

Text #18

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.1693. Min Act: -0.1700

Data Index: 4990865 (Open Web Text)

Max Activating Token Index: 464

Text #19

Max Range: 4.3810. Min Range: -4.3810

Max Act: 4.1273. Min Act: -0.1700

Data Index: 7930407 (Open Web Text)

Max Activating Token Index: 333