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

Dataset: Open Web Text

Neuron 978 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: 4.0278. Min Range: -4.0278

Max Act: 4.0278. Min Act: -0.1700

Data Index: 6117172 (Open Web Text)

Max Activating Token Index: 386

Text #1

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.9727. Min Act: -0.1700

Data Index: 2475360 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.9063. Min Act: -0.1700

Data Index: 7012651 (Open Web Text)

Max Activating Token Index: 662

Text #3

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.8836. Min Act: -0.1700

Data Index: 1562592 (Open Web Text)

Max Activating Token Index: 509

Text #4

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.8517. Min Act: -0.1700

Data Index: 5371342 (Open Web Text)

Max Activating Token Index: 509

Text #5

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.8198. Min Act: -0.1700

Data Index: 7588102 (Open Web Text)

Max Activating Token Index: 64

Text #6

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.8370. Min Act: -0.1700

Data Index: 2983779 (Open Web Text)

Max Activating Token Index: 603

Text #7

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.8430. Min Act: -0.1700

Data Index: 2475359 (Open Web Text)

Max Activating Token Index: 974

Text #8

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.8372. Min Act: -0.1700

Data Index: 4987968 (Open Web Text)

Max Activating Token Index: 376

Text #9

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.8285. Min Act: -0.1700

Data Index: 7107514 (Open Web Text)

Max Activating Token Index: 861

Text #10

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.7909. Min Act: -0.1700

Data Index: 8332234 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.7524. Min Act: -0.1700

Data Index: 6363344 (Open Web Text)

Max Activating Token Index: 981

Text #12

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.7754. Min Act: -0.1700

Data Index: 989973 (Open Web Text)

Max Activating Token Index: 78

Text #13

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.7342. Min Act: -0.1700

Data Index: 4530046 (Open Web Text)

Max Activating Token Index: 894

Text #14

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.7184. Min Act: -0.1700

Data Index: 4680029 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.7533. Min Act: -0.1700

Data Index: 6434129 (Open Web Text)

Max Activating Token Index: 529

Text #16

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.7434. Min Act: -0.1700

Data Index: 6977825 (Open Web Text)

Max Activating Token Index: 408

Text #17

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.7581. Min Act: -0.1700

Data Index: 2574015 (Open Web Text)

Max Activating Token Index: 751

Text #18

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.6963. Min Act: -0.1700

Data Index: 2758382 (Open Web Text)

Max Activating Token Index: 372

Text #19

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.7139. Min Act: -0.1700

Data Index: 7211056 (Open Web Text)

Max Activating Token Index: 950