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

Dataset: Open Web Text

Neuron 2917 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: 1.4767. Min Range: -1.4767

Max Act: 1.4767. Min Act: -0.1700

Data Index: 2906131 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4722. Min Act: -0.1664

Data Index: 2741748 (Open Web Text)

Max Activating Token Index: 601

Text #2

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4727. Min Act: -0.1683

Data Index: 6772491 (Open Web Text)

Max Activating Token Index: 265

Text #3

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4664. Min Act: -0.1700

Data Index: 191354 (Open Web Text)

Max Activating Token Index: 858

Text #4

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4683. Min Act: -0.1700

Data Index: 2747646 (Open Web Text)

Max Activating Token Index: 62

Text #5

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4604. Min Act: -0.1700

Data Index: 8206022 (Open Web Text)

Max Activating Token Index: 32

Text #6

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4715. Min Act: -0.1700

Data Index: 6329714 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4694. Min Act: -0.1699

Data Index: 3743543 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4605. Min Act: -0.1700

Data Index: 2649651 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4567. Min Act: -0.1700

Data Index: 5904158 (Open Web Text)

Max Activating Token Index: 105

Text #10

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4458. Min Act: -0.1700

Data Index: 6763788 (Open Web Text)

Max Activating Token Index: 159

Text #11

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4562. Min Act: -0.1700

Data Index: 2734954 (Open Web Text)

Max Activating Token Index: 812

Text #12

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4450. Min Act: -0.1700

Data Index: 2962978 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4543. Min Act: -0.1700

Data Index: 8125347 (Open Web Text)

Max Activating Token Index: 292

Text #14

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4495. Min Act: -0.1700

Data Index: 4274757 (Open Web Text)

Max Activating Token Index: 998

Text #15

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4366. Min Act: -0.1700

Data Index: 942159 (Open Web Text)

Max Activating Token Index: 795

Text #16

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4449. Min Act: -0.1700

Data Index: 7367418 (Open Web Text)

Max Activating Token Index: 143

Text #17

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4476. Min Act: -0.1700

Data Index: 1485736 (Open Web Text)

Max Activating Token Index: 271

Text #18

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4575. Min Act: -0.1700

Data Index: 6155897 (Open Web Text)

Max Activating Token Index: 810

Text #19

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4497. Min Act: -0.1700

Data Index: 1532825 (Open Web Text)

Max Activating Token Index: 1022