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

Dataset: Open Web Text

Neuron 1974 in Layer 1

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: 2.0490. Min Range: -2.0490

Max Act: 2.0490. Min Act: -0.1700

Data Index: 3803680 (Open Web Text)

Max Activating Token Index: 222

Text #1

Max Range: 2.0490. Min Range: -2.0490

Max Act: 2.0178. Min Act: -0.1700

Data Index: 4964181 (Open Web Text)

Max Activating Token Index: 106

Text #2

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9931. Min Act: -0.1694

Data Index: 7400150 (Open Web Text)

Max Activating Token Index: 266

Text #3

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9678. Min Act: -0.1700

Data Index: 8709666 (Open Web Text)

Max Activating Token Index: 119

Text #4

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9727. Min Act: -0.1694

Data Index: 7347099 (Open Web Text)

Max Activating Token Index: 153

Text #5

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9621. Min Act: -0.1700

Data Index: 4577198 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9568. Min Act: -0.1700

Data Index: 6798579 (Open Web Text)

Max Activating Token Index: 25

Text #7

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9661. Min Act: -0.1699

Data Index: 2600254 (Open Web Text)

Max Activating Token Index: 183

Text #8

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9600. Min Act: -0.1700

Data Index: 3429672 (Open Web Text)

Max Activating Token Index: 146

Text #9

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9499. Min Act: -0.1700

Data Index: 4412166 (Open Web Text)

Max Activating Token Index: 163

Text #10

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9488. Min Act: -0.1700

Data Index: 6253606 (Open Web Text)

Max Activating Token Index: 141

Text #11

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9490. Min Act: -0.1700

Data Index: 8418600 (Open Web Text)

Max Activating Token Index: 110

Text #12

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9445. Min Act: -0.1700

Data Index: 2660545 (Open Web Text)

Max Activating Token Index: 819

Text #13

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9386. Min Act: -0.1700

Data Index: 505482 (Open Web Text)

Max Activating Token Index: 150

Text #14

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9289. Min Act: -0.1700

Data Index: 3086588 (Open Web Text)

Max Activating Token Index: 139

Text #15

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9248. Min Act: -0.1699

Data Index: 6814614 (Open Web Text)

Max Activating Token Index: 670

Text #16

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9306. Min Act: -0.1700

Data Index: 3760518 (Open Web Text)

Max Activating Token Index: 264

Text #17

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9193. Min Act: -0.1700

Data Index: 7419218 (Open Web Text)

Max Activating Token Index: 682

Text #18

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9276. Min Act: -0.1693

Data Index: 794324 (Open Web Text)

Max Activating Token Index: 206

Text #19

Max Range: 2.0490. Min Range: -2.0490

Max Act: 1.9255. Min Act: -0.1700

Data Index: 2361116 (Open Web Text)

Max Activating Token Index: 299