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

Dataset: Open Web Text

Neuron 2187 in Layer 0

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: 3.0448. Min Range: -3.0448

Max Act: 3.0448. Min Act: -0.1700

Data Index: 4305368 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9289. Min Act: -0.1700

Data Index: 5463924 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9011. Min Act: -0.1700

Data Index: 1400265 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9084. Min Act: -0.1700

Data Index: 8030468 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8980. Min Act: -0.1700

Data Index: 5114326 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8730. Min Act: -0.1700

Data Index: 2316341 (Open Web Text)

Max Activating Token Index: 125

Text #6

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8834. Min Act: -0.1700

Data Index: 7761194 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8685. Min Act: -0.1700

Data Index: 2546916 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8727. Min Act: -0.1700

Data Index: 8083991 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8900. Min Act: -0.1700

Data Index: 4696706 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8896. Min Act: -0.1700

Data Index: 3390279 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8921. Min Act: -0.1700

Data Index: 8082921 (Open Web Text)

Max Activating Token Index: 40

Text #12

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8715. Min Act: -0.1700

Data Index: 4781259 (Open Web Text)

Max Activating Token Index: 91

Text #13

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8689. Min Act: -0.1700

Data Index: 5508510 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8643. Min Act: -0.1700

Data Index: 3283779 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8533. Min Act: -0.1700

Data Index: 3242746 (Open Web Text)

Max Activating Token Index: 743

Text #16

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8647. Min Act: -0.1700

Data Index: 7646009 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8487. Min Act: -0.1700

Data Index: 5009906 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8401. Min Act: -0.1700

Data Index: 1620420 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.8527. Min Act: -0.1700

Data Index: 2886742 (Open Web Text)

Max Activating Token Index: 5