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

Dataset: Open Web Text

Neuron 1148 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: 4.2092. Min Range: -4.2092

Max Act: 4.2092. Min Act: -0.1700

Data Index: 3631954 (Open Web Text)

Max Activating Token Index: 980

Text #1

Max Range: 4.2092. Min Range: -4.2092

Max Act: 4.1736. Min Act: -0.1700

Data Index: 808747 (Open Web Text)

Max Activating Token Index: 316

Text #2

Max Range: 4.2092. Min Range: -4.2092

Max Act: 4.1378. Min Act: -0.1700

Data Index: 1458132 (Open Web Text)

Max Activating Token Index: 174

Text #3

Max Range: 4.2092. Min Range: -4.2092

Max Act: 4.0745. Min Act: -0.1700

Data Index: 2069489 (Open Web Text)

Max Activating Token Index: 456

Text #4

Max Range: 4.2092. Min Range: -4.2092

Max Act: 4.0882. Min Act: -0.1700

Data Index: 6483975 (Open Web Text)

Max Activating Token Index: 739

Text #5

Max Range: 4.2092. Min Range: -4.2092

Max Act: 4.0654. Min Act: -0.1700

Data Index: 1556058 (Open Web Text)

Max Activating Token Index: 917

Text #6

Max Range: 4.2092. Min Range: -4.2092

Max Act: 4.0060. Min Act: -0.1700

Data Index: 1767244 (Open Web Text)

Max Activating Token Index: 133

Text #7

Max Range: 4.2092. Min Range: -4.2092

Max Act: 3.9964. Min Act: -0.1700

Data Index: 8562476 (Open Web Text)

Max Activating Token Index: 416

Text #8

Max Range: 4.2092. Min Range: -4.2092

Max Act: 4.0085. Min Act: -0.1700

Data Index: 798520 (Open Web Text)

Max Activating Token Index: 840

Text #9

Max Range: 4.2092. Min Range: -4.2092

Max Act: 4.0012. Min Act: -0.1700

Data Index: 4728008 (Open Web Text)

Max Activating Token Index: 116

Text #10

Max Range: 4.2092. Min Range: -4.2092

Max Act: 4.0093. Min Act: -0.1700

Data Index: 1560752 (Open Web Text)

Max Activating Token Index: 560

Text #11

Max Range: 4.2092. Min Range: -4.2092

Max Act: 3.9889. Min Act: -0.1700

Data Index: 1488540 (Open Web Text)

Max Activating Token Index: 63

Text #12

Max Range: 4.2092. Min Range: -4.2092

Max Act: 3.9921. Min Act: -0.1700

Data Index: 7268899 (Open Web Text)

Max Activating Token Index: 970

Text #13

Max Range: 4.2092. Min Range: -4.2092

Max Act: 4.0119. Min Act: -0.1700

Data Index: 4474255 (Open Web Text)

Max Activating Token Index: 668

Text #14

Max Range: 4.2092. Min Range: -4.2092

Max Act: 3.9903. Min Act: -0.1700

Data Index: 3052513 (Open Web Text)

Max Activating Token Index: 32

Text #15

Max Range: 4.2092. Min Range: -4.2092

Max Act: 3.9667. Min Act: -0.1700

Data Index: 2698181 (Open Web Text)

Max Activating Token Index: 811

Text #16

Max Range: 4.2092. Min Range: -4.2092

Max Act: 3.9901. Min Act: -0.1700

Data Index: 795125 (Open Web Text)

Max Activating Token Index: 476

Text #17

Max Range: 4.2092. Min Range: -4.2092

Max Act: 3.9804. Min Act: -0.1700

Data Index: 5210654 (Open Web Text)

Max Activating Token Index: 998

Text #18

Max Range: 4.2092. Min Range: -4.2092

Max Act: 3.9842. Min Act: -0.1700

Data Index: 4053383 (Open Web Text)

Max Activating Token Index: 693

Text #19

Max Range: 4.2092. Min Range: -4.2092

Max Act: 3.9567. Min Act: -0.1700

Data Index: 4648637 (Open Web Text)

Max Activating Token Index: 991