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

Dataset: Open Web Text

Neuron 1614 in Layer 0

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: 5.6926. Min Range: -5.6926

Max Act: 5.6926. Min Act: -0.1697

Data Index: 1443517 (Open Web Text)

Max Activating Token Index: 225

Text #1

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.6530. Min Act: -0.1630

Data Index: 6351395 (Open Web Text)

Max Activating Token Index: 84

Text #2

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.6699. Min Act: -0.1700

Data Index: 1443530 (Open Web Text)

Max Activating Token Index: 392

Text #3

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.6489. Min Act: -0.1693

Data Index: 7783047 (Open Web Text)

Max Activating Token Index: 106

Text #4

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5848. Min Act: -0.1700

Data Index: 6920497 (Open Web Text)

Max Activating Token Index: 128

Text #5

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5545. Min Act: -0.1700

Data Index: 7385250 (Open Web Text)

Max Activating Token Index: 111

Text #6

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5768. Min Act: -0.1697

Data Index: 7005744 (Open Web Text)

Max Activating Token Index: 146

Text #7

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5687. Min Act: -0.1700

Data Index: 7005743 (Open Web Text)

Max Activating Token Index: 110

Text #8

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5835. Min Act: -0.1698

Data Index: 4970901 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5655. Min Act: -0.1700

Data Index: 1676836 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5502. Min Act: -0.1700

Data Index: 6612114 (Open Web Text)

Max Activating Token Index: 68

Text #11

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5596. Min Act: -0.1700

Data Index: 6612119 (Open Web Text)

Max Activating Token Index: 89

Text #12

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5493. Min Act: -0.1700

Data Index: 1495213 (Open Web Text)

Max Activating Token Index: 919

Text #13

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5679. Min Act: -0.1688

Data Index: 5434035 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5570. Min Act: -0.1687

Data Index: 3794334 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5688. Min Act: -0.1699

Data Index: 4970915 (Open Web Text)

Max Activating Token Index: 69

Text #16

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5344. Min Act: -0.1695

Data Index: 5906852 (Open Web Text)

Max Activating Token Index: 113

Text #17

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5451. Min Act: -0.1666

Data Index: 3794318 (Open Web Text)

Max Activating Token Index: 72

Text #18

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5322. Min Act: -0.1700

Data Index: 1606652 (Open Web Text)

Max Activating Token Index: 134

Text #19

Max Range: 5.6926. Min Range: -5.6926

Max Act: 5.5389. Min Act: -0.1688

Data Index: 7122755 (Open Web Text)

Max Activating Token Index: 69