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

Dataset: Open Web Text

Neuron 24 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: 3.7643. Min Range: -3.7643

Max Act: 3.7643. Min Act: -0.1700

Data Index: 3030110 (Open Web Text)

Max Activating Token Index: 269

Text #1

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.7283. Min Act: -0.1700

Data Index: 7335646 (Open Web Text)

Max Activating Token Index: 148

Text #2

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.6836. Min Act: -0.1700

Data Index: 4992118 (Open Web Text)

Max Activating Token Index: 408

Text #3

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.6470. Min Act: -0.1700

Data Index: 3524125 (Open Web Text)

Max Activating Token Index: 590

Text #4

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.6136. Min Act: -0.1700

Data Index: 57802 (Open Web Text)

Max Activating Token Index: 604

Text #5

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.5442. Min Act: -0.1700

Data Index: 5502825 (Open Web Text)

Max Activating Token Index: 898

Text #6

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3879. Min Act: -0.1700

Data Index: 4254524 (Open Web Text)

Max Activating Token Index: 329

Text #7

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3744. Min Act: -0.1700

Data Index: 2553223 (Open Web Text)

Max Activating Token Index: 137

Text #8

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3798. Min Act: -0.1700

Data Index: 296138 (Open Web Text)

Max Activating Token Index: 178

Text #9

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3691. Min Act: -0.1700

Data Index: 3768925 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3589. Min Act: -0.1700

Data Index: 1534383 (Open Web Text)

Max Activating Token Index: 698

Text #11

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3584. Min Act: -0.1700

Data Index: 8543112 (Open Web Text)

Max Activating Token Index: 138

Text #12

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3709. Min Act: -0.1700

Data Index: 4210676 (Open Web Text)

Max Activating Token Index: 95

Text #13

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3389. Min Act: -0.1700

Data Index: 5315882 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3404. Min Act: -0.1700

Data Index: 6467514 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3406. Min Act: -0.1700

Data Index: 1607248 (Open Web Text)

Max Activating Token Index: 664

Text #16

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3133. Min Act: -0.1700

Data Index: 3445168 (Open Web Text)

Max Activating Token Index: 264

Text #17

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3223. Min Act: -0.1700

Data Index: 5867613 (Open Web Text)

Max Activating Token Index: 559

Text #18

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3335. Min Act: -0.1700

Data Index: 717697 (Open Web Text)

Max Activating Token Index: 293

Text #19

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.3096. Min Act: -0.1700

Data Index: 5235885 (Open Web Text)

Max Activating Token Index: 77