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

Dataset: Open Web Text

Neuron 2708 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: 3.3827. Min Range: -3.3827

Max Act: 3.3524. Min Act: -0.1700

Data Index: 4299246 (Open Web Text)

Max Activating Token Index: 952

Text #1

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3827. Min Act: -0.1700

Data Index: 3448015 (Open Web Text)

Max Activating Token Index: 437

Text #2

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3643. Min Act: -0.1700

Data Index: 4127050 (Open Web Text)

Max Activating Token Index: 693

Text #3

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3611. Min Act: -0.1700

Data Index: 1034349 (Open Web Text)

Max Activating Token Index: 483

Text #4

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3662. Min Act: -0.1700

Data Index: 7403040 (Open Web Text)

Max Activating Token Index: 674

Text #5

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3616. Min Act: -0.1700

Data Index: 474995 (Open Web Text)

Max Activating Token Index: 564

Text #6

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3312. Min Act: -0.1700

Data Index: 1105330 (Open Web Text)

Max Activating Token Index: 347

Text #7

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3369. Min Act: -0.1700

Data Index: 6441171 (Open Web Text)

Max Activating Token Index: 457

Text #8

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3291. Min Act: -0.1700

Data Index: 4299247 (Open Web Text)

Max Activating Token Index: 909

Text #9

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3185. Min Act: -0.1700

Data Index: 4698457 (Open Web Text)

Max Activating Token Index: 760

Text #10

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3310. Min Act: -0.1700

Data Index: 6022665 (Open Web Text)

Max Activating Token Index: 809

Text #11

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3129. Min Act: -0.1700

Data Index: 87194 (Open Web Text)

Max Activating Token Index: 940

Text #12

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3129. Min Act: -0.1700

Data Index: 656593 (Open Web Text)

Max Activating Token Index: 334

Text #13

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3220. Min Act: -0.1700

Data Index: 3922653 (Open Web Text)

Max Activating Token Index: 667

Text #14

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.2927. Min Act: -0.1700

Data Index: 7092508 (Open Web Text)

Max Activating Token Index: 479

Text #15

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.2884. Min Act: -0.1700

Data Index: 4111834 (Open Web Text)

Max Activating Token Index: 601

Text #16

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.2712. Min Act: -0.1700

Data Index: 5301212 (Open Web Text)

Max Activating Token Index: 357

Text #17

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.2721. Min Act: -0.1700

Data Index: 4213518 (Open Web Text)

Max Activating Token Index: 74

Text #18

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.2655. Min Act: -0.1700

Data Index: 7164108 (Open Web Text)

Max Activating Token Index: 735

Text #19

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.2675. Min Act: -0.1700

Data Index: 3533431 (Open Web Text)

Max Activating Token Index: 751