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

Dataset: Open Web Text

Neuron 2931 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: 3.0140. Min Range: -3.0140

Max Act: 3.0140. Min Act: -0.1700

Data Index: 5442284 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.0140. Min Range: -3.0140

Max Act: 3.0030. Min Act: -0.1700

Data Index: 1326157 (Open Web Text)

Max Activating Token Index: 559

Text #2

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9637. Min Act: -0.1700

Data Index: 7580033 (Open Web Text)

Max Activating Token Index: 845

Text #3

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9388. Min Act: -0.1700

Data Index: 1207135 (Open Web Text)

Max Activating Token Index: 499

Text #4

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9051. Min Act: -0.1700

Data Index: 1771352 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.8607. Min Act: -0.1700

Data Index: 6418466 (Open Web Text)

Max Activating Token Index: 352

Text #6

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.8843. Min Act: -0.1700

Data Index: 6475927 (Open Web Text)

Max Activating Token Index: 502

Text #7

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.8433. Min Act: -0.1700

Data Index: 1597828 (Open Web Text)

Max Activating Token Index: 579

Text #8

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.8360. Min Act: -0.1700

Data Index: 5920978 (Open Web Text)

Max Activating Token Index: 541

Text #9

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.8272. Min Act: -0.1700

Data Index: 1335893 (Open Web Text)

Max Activating Token Index: 280

Text #10

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.8082. Min Act: -0.1700

Data Index: 5892129 (Open Web Text)

Max Activating Token Index: 784

Text #11

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.8038. Min Act: -0.1700

Data Index: 941838 (Open Web Text)

Max Activating Token Index: 787

Text #12

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.8140. Min Act: -0.1700

Data Index: 4580948 (Open Web Text)

Max Activating Token Index: 505

Text #13

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.7600. Min Act: -0.1700

Data Index: 7017211 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.7792. Min Act: -0.1700

Data Index: 5462310 (Open Web Text)

Max Activating Token Index: 979

Text #15

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.7765. Min Act: -0.1700

Data Index: 897316 (Open Web Text)

Max Activating Token Index: 545

Text #16

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.7741. Min Act: -0.1700

Data Index: 1869891 (Open Web Text)

Max Activating Token Index: 179

Text #17

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.7596. Min Act: -0.1700

Data Index: 6577653 (Open Web Text)

Max Activating Token Index: 379

Text #18

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.7602. Min Act: -0.1700

Data Index: 978781 (Open Web Text)

Max Activating Token Index: 937

Text #19

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.7630. Min Act: -0.1700

Data Index: 3149969 (Open Web Text)

Max Activating Token Index: 965