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

Dataset: Open Web Text

Neuron 128 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: 3.0729. Min Range: -3.0729

Max Act: 3.0729. Min Act: -0.1700

Data Index: 4543583 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.0729. Min Range: -3.0729

Max Act: 3.0468. Min Act: -0.1700

Data Index: 2054803 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.0729. Min Range: -3.0729

Max Act: 3.0263. Min Act: -0.1700

Data Index: 5747803 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.0729. Min Range: -3.0729

Max Act: 3.0259. Min Act: -0.1700

Data Index: 3170376 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.0729. Min Range: -3.0729

Max Act: 3.0144. Min Act: -0.1700

Data Index: 5907241 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.0729. Min Range: -3.0729

Max Act: 3.0239. Min Act: -0.1700

Data Index: 8487300 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9973. Min Act: -0.1700

Data Index: 2553083 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9914. Min Act: -0.1700

Data Index: 5246148 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9893. Min Act: -0.1700

Data Index: 7050966 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9869. Min Act: -0.1700

Data Index: 7072778 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9762. Min Act: -0.1700

Data Index: 1507708 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9705. Min Act: -0.1700

Data Index: 8455755 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9715. Min Act: -0.1700

Data Index: 3779478 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9643. Min Act: -0.1700

Data Index: 6362081 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9598. Min Act: -0.1700

Data Index: 15649 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9648. Min Act: -0.1700

Data Index: 5313800 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9715. Min Act: -0.1700

Data Index: 758695 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9598. Min Act: -0.1700

Data Index: 1603883 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9496. Min Act: -0.1700

Data Index: 6951749 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.0729. Min Range: -3.0729

Max Act: 2.9514. Min Act: -0.1700

Data Index: 4885598 (Open Web Text)

Max Activating Token Index: 6