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

Dataset: Open Web Text

Neuron 1729 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: 5.1120. Min Range: -5.1120

Max Act: 5.0798. Min Act: -0.1700

Data Index: 8147766 (Open Web Text)

Max Activating Token Index: 73

Text #1

Max Range: 5.1120. Min Range: -5.1120

Max Act: 5.1120. Min Act: -0.1700

Data Index: 8057319 (Open Web Text)

Max Activating Token Index: 163

Text #2

Max Range: 5.1120. Min Range: -5.1120

Max Act: 5.0044. Min Act: -0.1700

Data Index: 1354532 (Open Web Text)

Max Activating Token Index: 883

Text #3

Max Range: 5.1120. Min Range: -5.1120

Max Act: 5.0282. Min Act: -0.1700

Data Index: 7686449 (Open Web Text)

Max Activating Token Index: 321

Text #4

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8891. Min Act: -0.1700

Data Index: 5120071 (Open Web Text)

Max Activating Token Index: 353

Text #5

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.9050. Min Act: -0.1700

Data Index: 168963 (Open Web Text)

Max Activating Token Index: 225

Text #6

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.9012. Min Act: -0.1700

Data Index: 7789624 (Open Web Text)

Max Activating Token Index: 1015

Text #7

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8533. Min Act: -0.1700

Data Index: 196994 (Open Web Text)

Max Activating Token Index: 832

Text #8

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.9248. Min Act: -0.1700

Data Index: 2012917 (Open Web Text)

Max Activating Token Index: 588

Text #9

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8757. Min Act: -0.1700

Data Index: 2395739 (Open Web Text)

Max Activating Token Index: 573

Text #10

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8636. Min Act: -0.1700

Data Index: 7381310 (Open Web Text)

Max Activating Token Index: 709

Text #11

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8345. Min Act: -0.1700

Data Index: 8153565 (Open Web Text)

Max Activating Token Index: 465

Text #12

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8313. Min Act: -0.1700

Data Index: 4390991 (Open Web Text)

Max Activating Token Index: 346

Text #13

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.7897. Min Act: -0.1700

Data Index: 5956316 (Open Web Text)

Max Activating Token Index: 615

Text #14

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8192. Min Act: -0.1700

Data Index: 2662838 (Open Web Text)

Max Activating Token Index: 909

Text #15

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8016. Min Act: -0.1700

Data Index: 2023235 (Open Web Text)

Max Activating Token Index: 321

Text #16

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8418. Min Act: -0.1700

Data Index: 4095259 (Open Web Text)

Max Activating Token Index: 421

Text #17

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8143. Min Act: -0.1700

Data Index: 4719012 (Open Web Text)

Max Activating Token Index: 878

Text #18

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8242. Min Act: -0.1700

Data Index: 1669908 (Open Web Text)

Max Activating Token Index: 430

Text #19

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8318. Min Act: -0.1700

Data Index: 3810750 (Open Web Text)

Max Activating Token Index: 915