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

Dataset: Open Web Text

Neuron 3070 in Layer 2

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: 4.0016. Min Range: -4.0016

Max Act: 4.0016. Min Act: -0.1700

Data Index: 8604126 (Open Web Text)

Max Activating Token Index: 27

Text #1

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.8913. Min Act: -0.1700

Data Index: 3132011 (Open Web Text)

Max Activating Token Index: 969

Text #2

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.8694. Min Act: -0.1700

Data Index: 4521113 (Open Web Text)

Max Activating Token Index: 40

Text #3

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.8439. Min Act: -0.1700

Data Index: 2413712 (Open Web Text)

Max Activating Token Index: 306

Text #4

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.8512. Min Act: -0.1700

Data Index: 833638 (Open Web Text)

Max Activating Token Index: 577

Text #5

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7717. Min Act: -0.1700

Data Index: 6163125 (Open Web Text)

Max Activating Token Index: 595

Text #6

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7518. Min Act: -0.1700

Data Index: 4416098 (Open Web Text)

Max Activating Token Index: 990

Text #7

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7730. Min Act: -0.1700

Data Index: 6096581 (Open Web Text)

Max Activating Token Index: 521

Text #8

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7450. Min Act: -0.1700

Data Index: 7629819 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7567. Min Act: -0.1700

Data Index: 6497072 (Open Web Text)

Max Activating Token Index: 896

Text #10

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7601. Min Act: -0.1700

Data Index: 4477042 (Open Web Text)

Max Activating Token Index: 836

Text #11

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7407. Min Act: -0.1700

Data Index: 3196958 (Open Web Text)

Max Activating Token Index: 587

Text #12

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7206. Min Act: -0.1700

Data Index: 4785207 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7260. Min Act: -0.1700

Data Index: 1746336 (Open Web Text)

Max Activating Token Index: 100

Text #14

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7128. Min Act: -0.1700

Data Index: 438256 (Open Web Text)

Max Activating Token Index: 72

Text #15

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7038. Min Act: -0.1700

Data Index: 4960579 (Open Web Text)

Max Activating Token Index: 458

Text #16

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.7145. Min Act: -0.1700

Data Index: 1208034 (Open Web Text)

Max Activating Token Index: 23

Text #17

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.6749. Min Act: -0.1700

Data Index: 4325217 (Open Web Text)

Max Activating Token Index: 972

Text #18

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.6982. Min Act: -0.1700

Data Index: 564874 (Open Web Text)

Max Activating Token Index: 33

Text #19

Max Range: 4.0016. Min Range: -4.0016

Max Act: 3.6923. Min Act: -0.1700

Data Index: 925039 (Open Web Text)

Max Activating Token Index: 61