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

Dataset: Open Web Text

Neuron 2626 in Layer 5

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: 4.4986. Min Range: -4.4986

Max Act: 4.4986. Min Act: -0.1700

Data Index: 1071257 (Open Web Text)

Max Activating Token Index: 447

Text #1

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4553. Min Act: -0.1700

Data Index: 6808904 (Open Web Text)

Max Activating Token Index: 112

Text #2

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4538. Min Act: -0.1700

Data Index: 2300052 (Open Web Text)

Max Activating Token Index: 404

Text #3

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4581. Min Act: -0.1700

Data Index: 5622328 (Open Web Text)

Max Activating Token Index: 684

Text #4

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4666. Min Act: -0.1700

Data Index: 3547365 (Open Web Text)

Max Activating Token Index: 596

Text #5

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4228. Min Act: -0.1700

Data Index: 7285044 (Open Web Text)

Max Activating Token Index: 692

Text #6

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4454. Min Act: -0.1700

Data Index: 1557671 (Open Web Text)

Max Activating Token Index: 475

Text #7

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3912. Min Act: -0.1700

Data Index: 5553646 (Open Web Text)

Max Activating Token Index: 237

Text #8

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4188. Min Act: -0.1700

Data Index: 1707435 (Open Web Text)

Max Activating Token Index: 944

Text #9

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3822. Min Act: -0.1700

Data Index: 7615349 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4177. Min Act: -0.1700

Data Index: 4514347 (Open Web Text)

Max Activating Token Index: 40

Text #11

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3922. Min Act: -0.1700

Data Index: 6020037 (Open Web Text)

Max Activating Token Index: 398

Text #12

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.4148. Min Act: -0.1700

Data Index: 4153263 (Open Web Text)

Max Activating Token Index: 595

Text #13

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3425. Min Act: -0.1700

Data Index: 3153500 (Open Web Text)

Max Activating Token Index: 1003

Text #14

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3691. Min Act: -0.1700

Data Index: 6245463 (Open Web Text)

Max Activating Token Index: 108

Text #15

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3203. Min Act: -0.1700

Data Index: 4507426 (Open Web Text)

Max Activating Token Index: 330

Text #16

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3461. Min Act: -0.1700

Data Index: 4586629 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3512. Min Act: -0.1700

Data Index: 391074 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3809. Min Act: -0.1700

Data Index: 1475847 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 4.4986. Min Range: -4.4986

Max Act: 4.3552. Min Act: -0.1700

Data Index: 169635 (Open Web Text)

Max Activating Token Index: 909