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

Dataset: Open Web Text

Neuron 2954 in Layer 4

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: 2.2835. Min Range: -2.2835

Max Act: 2.2835. Min Act: -0.1700

Data Index: 7615196 (Open Web Text)

Max Activating Token Index: 552

Text #1

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.2610. Min Act: -0.1700

Data Index: 753926 (Open Web Text)

Max Activating Token Index: 465

Text #2

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.2153. Min Act: -0.1700

Data Index: 5814626 (Open Web Text)

Max Activating Token Index: 152

Text #3

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.2001. Min Act: -0.1700

Data Index: 5695507 (Open Web Text)

Max Activating Token Index: 758

Text #4

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.2156. Min Act: -0.1700

Data Index: 2053407 (Open Web Text)

Max Activating Token Index: 574

Text #5

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1714. Min Act: -0.1700

Data Index: 8766915 (Open Web Text)

Max Activating Token Index: 850

Text #6

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1967. Min Act: -0.1700

Data Index: 4297159 (Open Web Text)

Max Activating Token Index: 105

Text #7

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1825. Min Act: -0.1700

Data Index: 7133437 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1793. Min Act: -0.1700

Data Index: 2855630 (Open Web Text)

Max Activating Token Index: 453

Text #9

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1700. Min Act: -0.1700

Data Index: 975650 (Open Web Text)

Max Activating Token Index: 768

Text #10

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1684. Min Act: -0.1700

Data Index: 3008561 (Open Web Text)

Max Activating Token Index: 105

Text #11

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1830. Min Act: -0.1700

Data Index: 4982333 (Open Web Text)

Max Activating Token Index: 721

Text #12

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1587. Min Act: -0.1700

Data Index: 6033717 (Open Web Text)

Max Activating Token Index: 257

Text #13

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1473. Min Act: -0.1700

Data Index: 2209673 (Open Web Text)

Max Activating Token Index: 881

Text #14

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1604. Min Act: -0.1700

Data Index: 6193819 (Open Web Text)

Max Activating Token Index: 186

Text #15

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1436. Min Act: -0.1700

Data Index: 2868616 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1591. Min Act: -0.1700

Data Index: 5428686 (Open Web Text)

Max Activating Token Index: 505

Text #17

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1613. Min Act: -0.1700

Data Index: 1153076 (Open Web Text)

Max Activating Token Index: 226

Text #18

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1658. Min Act: -0.1700

Data Index: 5368384 (Open Web Text)

Max Activating Token Index: 522

Text #19

Max Range: 2.2835. Min Range: -2.2835

Max Act: 2.1550. Min Act: -0.1700

Data Index: 1835715 (Open Web Text)

Max Activating Token Index: 552