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

Dataset: Open Web Text

Neuron 998 in Layer 0

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: 1.8700. Min Range: -1.8700

Max Act: 1.8700. Min Act: -0.1700

Data Index: 8240340 (Open Web Text)

Max Activating Token Index: 191

Text #1

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7615. Min Act: -0.1700

Data Index: 3892183 (Open Web Text)

Max Activating Token Index: 197

Text #2

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7454. Min Act: -0.1700

Data Index: 8333099 (Open Web Text)

Max Activating Token Index: 72

Text #3

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7370. Min Act: -0.1700

Data Index: 7733072 (Open Web Text)

Max Activating Token Index: 230

Text #4

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7297. Min Act: -0.1700

Data Index: 2510740 (Open Web Text)

Max Activating Token Index: 73

Text #5

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7335. Min Act: -0.1700

Data Index: 7340532 (Open Web Text)

Max Activating Token Index: 277

Text #6

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7028. Min Act: -0.1700

Data Index: 3603187 (Open Web Text)

Max Activating Token Index: 182

Text #7

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7064. Min Act: -0.1700

Data Index: 7761329 (Open Web Text)

Max Activating Token Index: 251

Text #8

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7155. Min Act: -0.1700

Data Index: 3238715 (Open Web Text)

Max Activating Token Index: 449

Text #9

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7048. Min Act: -0.1700

Data Index: 5149589 (Open Web Text)

Max Activating Token Index: 212

Text #10

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7012. Min Act: -0.1700

Data Index: 7677143 (Open Web Text)

Max Activating Token Index: 758

Text #11

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7095. Min Act: -0.1700

Data Index: 7314327 (Open Web Text)

Max Activating Token Index: 359

Text #12

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.6975. Min Act: -0.1700

Data Index: 4633797 (Open Web Text)

Max Activating Token Index: 236

Text #13

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.6824. Min Act: -0.1700

Data Index: 8791118 (Open Web Text)

Max Activating Token Index: 85

Text #14

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.6898. Min Act: -0.1700

Data Index: 2701278 (Open Web Text)

Max Activating Token Index: 218

Text #15

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.6892. Min Act: -0.1700

Data Index: 6758012 (Open Web Text)

Max Activating Token Index: 115

Text #16

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.6857. Min Act: -0.1700

Data Index: 4762528 (Open Web Text)

Max Activating Token Index: 817

Text #17

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.6619. Min Act: -0.1700

Data Index: 5342408 (Open Web Text)

Max Activating Token Index: 698

Text #18

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.6765. Min Act: -0.1700

Data Index: 2161731 (Open Web Text)

Max Activating Token Index: 114

Text #19

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.6704. Min Act: -0.1700

Data Index: 4354095 (Open Web Text)

Max Activating Token Index: 172