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

Dataset: Open Web Text

Neuron 1086 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: 4.0112. Min Range: -4.0112

Max Act: 4.0112. Min Act: -0.1700

Data Index: 2422714 (Open Web Text)

Max Activating Token Index: 983

Text #1

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9778. Min Act: -0.1700

Data Index: 5633680 (Open Web Text)

Max Activating Token Index: 168

Text #2

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9992. Min Act: -0.1700

Data Index: 7175075 (Open Web Text)

Max Activating Token Index: 943

Text #3

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9461. Min Act: -0.1700

Data Index: 2459818 (Open Web Text)

Max Activating Token Index: 66

Text #4

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9419. Min Act: -0.1700

Data Index: 3952300 (Open Web Text)

Max Activating Token Index: 184

Text #5

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9036. Min Act: -0.1700

Data Index: 677981 (Open Web Text)

Max Activating Token Index: 83

Text #6

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9299. Min Act: -0.1700

Data Index: 2521640 (Open Web Text)

Max Activating Token Index: 813

Text #7

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9120. Min Act: -0.1700

Data Index: 6647115 (Open Web Text)

Max Activating Token Index: 60

Text #8

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9032. Min Act: -0.1700

Data Index: 1748900 (Open Web Text)

Max Activating Token Index: 951

Text #9

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.8976. Min Act: -0.1700

Data Index: 5579260 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9165. Min Act: -0.1700

Data Index: 492870 (Open Web Text)

Max Activating Token Index: 193

Text #11

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9080. Min Act: -0.1700

Data Index: 3225304 (Open Web Text)

Max Activating Token Index: 824

Text #12

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9045. Min Act: -0.1700

Data Index: 744247 (Open Web Text)

Max Activating Token Index: 975

Text #13

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.8988. Min Act: -0.1700

Data Index: 6205376 (Open Web Text)

Max Activating Token Index: 976

Text #14

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.9096. Min Act: -0.1700

Data Index: 1492491 (Open Web Text)

Max Activating Token Index: 392

Text #15

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.8407. Min Act: -0.1700

Data Index: 3712790 (Open Web Text)

Max Activating Token Index: 972

Text #16

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.8683. Min Act: -0.1700

Data Index: 5004623 (Open Web Text)

Max Activating Token Index: 244

Text #17

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.8599. Min Act: -0.1700

Data Index: 949149 (Open Web Text)

Max Activating Token Index: 295

Text #18

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.8772. Min Act: -0.1700

Data Index: 4109337 (Open Web Text)

Max Activating Token Index: 955

Text #19

Max Range: 4.0112. Min Range: -4.0112

Max Act: 3.8704. Min Act: -0.1700

Data Index: 969989 (Open Web Text)

Max Activating Token Index: 19