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

Dataset: Open Web Text

Neuron 2350 in Layer 1

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: 2.6761. Min Range: -2.6761

Max Act: 2.6761. Min Act: -0.1700

Data Index: 6023747 (Open Web Text)

Max Activating Token Index: 83

Text #1

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5994. Min Act: -0.1699

Data Index: 7462097 (Open Web Text)

Max Activating Token Index: 228

Text #2

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5977. Min Act: -0.1700

Data Index: 4849052 (Open Web Text)

Max Activating Token Index: 103

Text #3

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5901. Min Act: -0.1698

Data Index: 5347808 (Open Web Text)

Max Activating Token Index: 36

Text #4

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5678. Min Act: -0.1700

Data Index: 6525270 (Open Web Text)

Max Activating Token Index: 404

Text #5

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5897. Min Act: -0.1700

Data Index: 8443161 (Open Web Text)

Max Activating Token Index: 129

Text #6

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5695. Min Act: -0.1700

Data Index: 2318899 (Open Web Text)

Max Activating Token Index: 318

Text #7

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5666. Min Act: -0.1700

Data Index: 3189610 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5532. Min Act: -0.1700

Data Index: 7103091 (Open Web Text)

Max Activating Token Index: 47

Text #9

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5343. Min Act: -0.1700

Data Index: 5538255 (Open Web Text)

Max Activating Token Index: 128

Text #10

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5228. Min Act: -0.1700

Data Index: 2634395 (Open Web Text)

Max Activating Token Index: 173

Text #11

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5354. Min Act: -0.1700

Data Index: 5572587 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5178. Min Act: -0.1700

Data Index: 6864931 (Open Web Text)

Max Activating Token Index: 100

Text #13

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5067. Min Act: -0.1700

Data Index: 2266277 (Open Web Text)

Max Activating Token Index: 297

Text #14

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5144. Min Act: -0.1700

Data Index: 7257748 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5267. Min Act: -0.1700

Data Index: 6719049 (Open Web Text)

Max Activating Token Index: 139

Text #16

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.4986. Min Act: -0.1700

Data Index: 2805237 (Open Web Text)

Max Activating Token Index: 226

Text #17

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5032. Min Act: -0.1700

Data Index: 2692170 (Open Web Text)

Max Activating Token Index: 124

Text #18

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.4977. Min Act: -0.1700

Data Index: 4799631 (Open Web Text)

Max Activating Token Index: 92

Text #19

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5001. Min Act: -0.1700

Data Index: 1061047 (Open Web Text)

Max Activating Token Index: 426