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

Dataset: Open Web Text

Neuron 1753 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: 4.7861. Min Range: -4.7861

Max Act: 4.7861. Min Act: -0.1700

Data Index: 2323554 (Open Web Text)

Max Activating Token Index: 768

Text #1

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.5040. Min Act: -0.1700

Data Index: 8792581 (Open Web Text)

Max Activating Token Index: 393

Text #2

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.4577. Min Act: -0.1700

Data Index: 267039 (Open Web Text)

Max Activating Token Index: 912

Text #3

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.4302. Min Act: -0.1700

Data Index: 2974983 (Open Web Text)

Max Activating Token Index: 793

Text #4

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3912. Min Act: -0.1700

Data Index: 4806725 (Open Web Text)

Max Activating Token Index: 462

Text #5

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3813. Min Act: -0.1700

Data Index: 1891172 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3875. Min Act: -0.1700

Data Index: 5676576 (Open Web Text)

Max Activating Token Index: 469

Text #7

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.4123. Min Act: -0.1700

Data Index: 1087488 (Open Web Text)

Max Activating Token Index: 35

Text #8

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3536. Min Act: -0.1700

Data Index: 7236356 (Open Web Text)

Max Activating Token Index: 358

Text #9

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3170. Min Act: -0.1700

Data Index: 8532857 (Open Web Text)

Max Activating Token Index: 513

Text #10

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.2857. Min Act: -0.1700

Data Index: 2842577 (Open Web Text)

Max Activating Token Index: 605

Text #11

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3350. Min Act: -0.1700

Data Index: 6372957 (Open Web Text)

Max Activating Token Index: 71

Text #12

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3500. Min Act: -0.1700

Data Index: 1279545 (Open Web Text)

Max Activating Token Index: 432

Text #13

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3252. Min Act: -0.1700

Data Index: 344778 (Open Web Text)

Max Activating Token Index: 578

Text #14

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3588. Min Act: -0.1700

Data Index: 7424049 (Open Web Text)

Max Activating Token Index: 545

Text #15

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3309. Min Act: -0.1700

Data Index: 4267562 (Open Web Text)

Max Activating Token Index: 511

Text #16

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3351. Min Act: -0.1700

Data Index: 8790202 (Open Web Text)

Max Activating Token Index: 492

Text #17

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3340. Min Act: -0.1700

Data Index: 8631538 (Open Web Text)

Max Activating Token Index: 739

Text #18

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.2658. Min Act: -0.1700

Data Index: 2367190 (Open Web Text)

Max Activating Token Index: 739

Text #19

Max Range: 4.7861. Min Range: -4.7861

Max Act: 4.3173. Min Act: -0.1700

Data Index: 8187218 (Open Web Text)

Max Activating Token Index: 865