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

Dataset: Open Web Text

Neuron 2213 in Layer 4

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: 4.8656. Min Range: -4.8656

Max Act: 4.8656. Min Act: -0.1700

Data Index: 1334185 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.6451. Min Act: -0.1700

Data Index: 3773150 (Open Web Text)

Max Activating Token Index: 191

Text #2

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.6217. Min Act: -0.1700

Data Index: 1577244 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.6082. Min Act: -0.1700

Data Index: 982546 (Open Web Text)

Max Activating Token Index: 877

Text #4

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.6229. Min Act: -0.1700

Data Index: 3471412 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.5621. Min Act: -0.1700

Data Index: 4254899 (Open Web Text)

Max Activating Token Index: 352

Text #6

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.5627. Min Act: -0.1699

Data Index: 5796304 (Open Web Text)

Max Activating Token Index: 254

Text #7

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.5496. Min Act: -0.1700

Data Index: 3863061 (Open Web Text)

Max Activating Token Index: 717

Text #8

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.5843. Min Act: -0.1700

Data Index: 5024603 (Open Web Text)

Max Activating Token Index: 175

Text #9

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.5742. Min Act: -0.1700

Data Index: 1094452 (Open Web Text)

Max Activating Token Index: 335

Text #10

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.4852. Min Act: -0.1700

Data Index: 4076138 (Open Web Text)

Max Activating Token Index: 477

Text #11

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.4962. Min Act: -0.1700

Data Index: 4164348 (Open Web Text)

Max Activating Token Index: 268

Text #12

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.5161. Min Act: -0.1700

Data Index: 5753262 (Open Web Text)

Max Activating Token Index: 859

Text #13

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.5111. Min Act: -0.1700

Data Index: 8206997 (Open Web Text)

Max Activating Token Index: 279

Text #14

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.5097. Min Act: -0.1700

Data Index: 611574 (Open Web Text)

Max Activating Token Index: 131

Text #15

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.4861. Min Act: -0.1700

Data Index: 7891167 (Open Web Text)

Max Activating Token Index: 236

Text #16

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.4464. Min Act: -0.1700

Data Index: 1938697 (Open Web Text)

Max Activating Token Index: 897

Text #17

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.4833. Min Act: -0.1700

Data Index: 1387263 (Open Web Text)

Max Activating Token Index: 613

Text #18

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.4804. Min Act: -0.1700

Data Index: 5111381 (Open Web Text)

Max Activating Token Index: 409

Text #19

Max Range: 4.8656. Min Range: -4.8656

Max Act: 4.4273. Min Act: -0.1700

Data Index: 4796005 (Open Web Text)

Max Activating Token Index: 579