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

Dataset: Open Web Text

Neuron 150 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: 3.0080. Min Range: -3.0080

Max Act: 3.0080. Min Act: -0.1700

Data Index: 6157654 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.9819. Min Act: -0.1700

Data Index: 5533699 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.9590. Min Act: -0.1700

Data Index: 2932941 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.9052. Min Act: -0.1700

Data Index: 6229226 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8886. Min Act: -0.1700

Data Index: 3716378 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8868. Min Act: -0.1700

Data Index: 5619408 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8598. Min Act: -0.1700

Data Index: 4737700 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8532. Min Act: -0.1700

Data Index: 5419270 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8600. Min Act: -0.1700

Data Index: 5965037 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8521. Min Act: -0.1700

Data Index: 4655910 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8475. Min Act: -0.1700

Data Index: 6741308 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8449. Min Act: -0.1700

Data Index: 8771833 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8487. Min Act: -0.1700

Data Index: 5571055 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8390. Min Act: -0.1700

Data Index: 5259146 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8321. Min Act: -0.1700

Data Index: 5288283 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8297. Min Act: -0.1700

Data Index: 3472399 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8352. Min Act: -0.1700

Data Index: 7894821 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8230. Min Act: -0.1700

Data Index: 5499987 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8213. Min Act: -0.1700

Data Index: 3940478 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8192. Min Act: -0.1700

Data Index: 3849050 (Open Web Text)

Max Activating Token Index: 6