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

Dataset: Open Web Text

Neuron 2600 in Layer 6

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: 4.3512. Min Range: -4.3512

Max Act: 4.3512. Min Act: -0.1700

Data Index: 3345695 (Open Web Text)

Max Activating Token Index: 545

Text #1

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.2255. Min Act: -0.1700

Data Index: 4756675 (Open Web Text)

Max Activating Token Index: 795

Text #2

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.2248. Min Act: -0.1700

Data Index: 195369 (Open Web Text)

Max Activating Token Index: 397

Text #3

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.1865. Min Act: -0.1700

Data Index: 7174750 (Open Web Text)

Max Activating Token Index: 197

Text #4

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.1453. Min Act: -0.1700

Data Index: 3049132 (Open Web Text)

Max Activating Token Index: 651

Text #5

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.1614. Min Act: -0.1700

Data Index: 4397302 (Open Web Text)

Max Activating Token Index: 1008

Text #6

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0651. Min Act: -0.1700

Data Index: 5640333 (Open Web Text)

Max Activating Token Index: 398

Text #7

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0436. Min Act: -0.1700

Data Index: 2451755 (Open Web Text)

Max Activating Token Index: 635

Text #8

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0747. Min Act: -0.1700

Data Index: 6291934 (Open Web Text)

Max Activating Token Index: 132

Text #9

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0668. Min Act: -0.1700

Data Index: 4146087 (Open Web Text)

Max Activating Token Index: 652

Text #10

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0309. Min Act: -0.1700

Data Index: 2797586 (Open Web Text)

Max Activating Token Index: 802

Text #11

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0202. Min Act: -0.1700

Data Index: 2602510 (Open Web Text)

Max Activating Token Index: 253

Text #12

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0164. Min Act: -0.1700

Data Index: 165088 (Open Web Text)

Max Activating Token Index: 159

Text #13

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0208. Min Act: -0.1700

Data Index: 6413698 (Open Web Text)

Max Activating Token Index: 682

Text #14

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0042. Min Act: -0.1700

Data Index: 6075082 (Open Web Text)

Max Activating Token Index: 819

Text #15

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0058. Min Act: -0.1700

Data Index: 278542 (Open Web Text)

Max Activating Token Index: 480

Text #16

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0288. Min Act: -0.1700

Data Index: 3607075 (Open Web Text)

Max Activating Token Index: 73

Text #17

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0117. Min Act: -0.1700

Data Index: 5513869 (Open Web Text)

Max Activating Token Index: 870

Text #18

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0006. Min Act: -0.1700

Data Index: 6974717 (Open Web Text)

Max Activating Token Index: 324

Text #19

Max Range: 4.3512. Min Range: -4.3512

Max Act: 4.0223. Min Act: -0.1700

Data Index: 3764312 (Open Web Text)

Max Activating Token Index: 287