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

Dataset: Open Web Text

Neuron 2251 in Layer 5

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: 4.0154. Min Range: -4.0154

Max Act: 3.9850. Min Act: -0.1700

Data Index: 7731990 (Open Web Text)

Max Activating Token Index: 482

Text #1

Max Range: 4.0154. Min Range: -4.0154

Max Act: 4.0154. Min Act: -0.1700

Data Index: 6441324 (Open Web Text)

Max Activating Token Index: 684

Text #2

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.9121. Min Act: -0.1700

Data Index: 7965591 (Open Web Text)

Max Activating Token Index: 556

Text #3

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.7814. Min Act: -0.1700

Data Index: 4832816 (Open Web Text)

Max Activating Token Index: 661

Text #4

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.7673. Min Act: -0.1700

Data Index: 5923349 (Open Web Text)

Max Activating Token Index: 734

Text #5

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.7492. Min Act: -0.1700

Data Index: 155498 (Open Web Text)

Max Activating Token Index: 410

Text #6

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.7359. Min Act: -0.1700

Data Index: 2609126 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.7033. Min Act: -0.1700

Data Index: 6035666 (Open Web Text)

Max Activating Token Index: 988

Text #8

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6927. Min Act: -0.1700

Data Index: 6911468 (Open Web Text)

Max Activating Token Index: 382

Text #9

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1195629 (Open Web Text)

Max Activating Token Index: 249

Text #10

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6695. Min Act: -0.1700

Data Index: 6301630 (Open Web Text)

Max Activating Token Index: 277

Text #11

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6495. Min Act: -0.1700

Data Index: 2261610 (Open Web Text)

Max Activating Token Index: 427

Text #12

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6422. Min Act: -0.1700

Data Index: 5882553 (Open Web Text)

Max Activating Token Index: 528

Text #13

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6698. Min Act: -0.1700

Data Index: 2927734 (Open Web Text)

Max Activating Token Index: 161

Text #14

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6610. Min Act: -0.1700

Data Index: 7288844 (Open Web Text)

Max Activating Token Index: 912

Text #15

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.5690. Min Act: -0.1700

Data Index: 8332325 (Open Web Text)

Max Activating Token Index: 909

Text #16

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6073. Min Act: -0.1700

Data Index: 7306674 (Open Web Text)

Max Activating Token Index: 484

Text #17

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6094. Min Act: -0.1700

Data Index: 3448619 (Open Web Text)

Max Activating Token Index: 228

Text #18

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6221. Min Act: -0.1700

Data Index: 5876575 (Open Web Text)

Max Activating Token Index: 494

Text #19

Max Range: 4.0154. Min Range: -4.0154

Max Act: 3.6105. Min Act: -0.1700

Data Index: 7045881 (Open Web Text)

Max Activating Token Index: 881