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

Dataset: Open Web Text

Neuron 826 in Layer 6

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: 3.9858. Min Range: -3.9858

Max Act: 3.9858. Min Act: -0.1700

Data Index: 8030904 (Open Web Text)

Max Activating Token Index: 479

Text #1

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.8862. Min Act: -0.1700

Data Index: 5428846 (Open Web Text)

Max Activating Token Index: 50

Text #2

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.8838. Min Act: -0.1700

Data Index: 2249920 (Open Web Text)

Max Activating Token Index: 122

Text #3

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7886. Min Act: -0.1700

Data Index: 3389903 (Open Web Text)

Max Activating Token Index: 195

Text #4

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.8025. Min Act: -0.1700

Data Index: 5306600 (Open Web Text)

Max Activating Token Index: 107

Text #5

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7683. Min Act: -0.1700

Data Index: 2837276 (Open Web Text)

Max Activating Token Index: 950

Text #6

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7462. Min Act: -0.1700

Data Index: 329102 (Open Web Text)

Max Activating Token Index: 545

Text #7

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7590. Min Act: -0.1700

Data Index: 4270174 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7635. Min Act: -0.1700

Data Index: 1561677 (Open Web Text)

Max Activating Token Index: 959

Text #9

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7193. Min Act: -0.1700

Data Index: 5269674 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7450. Min Act: -0.1700

Data Index: 8178791 (Open Web Text)

Max Activating Token Index: 180

Text #11

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7424. Min Act: -0.1700

Data Index: 3737797 (Open Web Text)

Max Activating Token Index: 188

Text #12

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7114. Min Act: -0.1700

Data Index: 5559407 (Open Web Text)

Max Activating Token Index: 165

Text #13

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.6770. Min Act: -0.1700

Data Index: 4272152 (Open Web Text)

Max Activating Token Index: 557

Text #14

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7298. Min Act: -0.1700

Data Index: 5336991 (Open Web Text)

Max Activating Token Index: 717

Text #15

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7084. Min Act: -0.1700

Data Index: 3582079 (Open Web Text)

Max Activating Token Index: 391

Text #16

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7051. Min Act: -0.1700

Data Index: 3152749 (Open Web Text)

Max Activating Token Index: 236

Text #17

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.6908. Min Act: -0.1700

Data Index: 2018665 (Open Web Text)

Max Activating Token Index: 256

Text #18

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.6846. Min Act: -0.1700

Data Index: 3535440 (Open Web Text)

Max Activating Token Index: 1019

Text #19

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.7106. Min Act: -0.1700

Data Index: 4371423 (Open Web Text)

Max Activating Token Index: 855