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

Dataset: Open Web Text

Neuron 1736 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: 1.7864. Min Range: -1.7864

Max Act: 1.7864. Min Act: -0.1700

Data Index: 1539938 (Open Web Text)

Max Activating Token Index: 105

Text #1

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7443. Min Act: -0.1700

Data Index: 7914476 (Open Web Text)

Max Activating Token Index: 736

Text #2

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7353. Min Act: -0.1700

Data Index: 7600822 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7336. Min Act: -0.1700

Data Index: 8652233 (Open Web Text)

Max Activating Token Index: 243

Text #4

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7273. Min Act: -0.1700

Data Index: 6935140 (Open Web Text)

Max Activating Token Index: 142

Text #5

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7230. Min Act: -0.1700

Data Index: 8768349 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7280. Min Act: -0.1700

Data Index: 4491093 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7183. Min Act: -0.1700

Data Index: 5570133 (Open Web Text)

Max Activating Token Index: 91

Text #8

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7121. Min Act: -0.1700

Data Index: 3835385 (Open Web Text)

Max Activating Token Index: 647

Text #9

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7152. Min Act: -0.1700

Data Index: 3111017 (Open Web Text)

Max Activating Token Index: 246

Text #10

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7144. Min Act: -0.1700

Data Index: 8422323 (Open Web Text)

Max Activating Token Index: 117

Text #11

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7100. Min Act: -0.1700

Data Index: 1638167 (Open Web Text)

Max Activating Token Index: 138

Text #12

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7006. Min Act: -0.1700

Data Index: 8670811 (Open Web Text)

Max Activating Token Index: 654

Text #13

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.7004. Min Act: -0.1700

Data Index: 887878 (Open Web Text)

Max Activating Token Index: 453

Text #14

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.6962. Min Act: -0.1700

Data Index: 1700866 (Open Web Text)

Max Activating Token Index: 590

Text #15

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.6942. Min Act: -0.1700

Data Index: 5190070 (Open Web Text)

Max Activating Token Index: 197

Text #16

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.6922. Min Act: -0.1700

Data Index: 4287532 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.6999. Min Act: -0.1700

Data Index: 4054745 (Open Web Text)

Max Activating Token Index: 795

Text #18

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.6984. Min Act: -0.1700

Data Index: 3237363 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 1.7864. Min Range: -1.7864

Max Act: 1.6907. Min Act: -0.1700

Data Index: 7543274 (Open Web Text)

Max Activating Token Index: 59