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

Dataset: Open Web Text

Neuron 625 in Layer 4

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: 3.0333. Min Range: -3.0333

Max Act: 3.0305. Min Act: -0.1700

Data Index: 4523822 (Open Web Text)

Max Activating Token Index: 987

Text #1

Max Range: 3.0333. Min Range: -3.0333

Max Act: 3.0333. Min Act: -0.1700

Data Index: 6829542 (Open Web Text)

Max Activating Token Index: 482

Text #2

Max Range: 3.0333. Min Range: -3.0333

Max Act: 3.0277. Min Act: -0.1700

Data Index: 4999537 (Open Web Text)

Max Activating Token Index: 107

Text #3

Max Range: 3.0333. Min Range: -3.0333

Max Act: 3.0019. Min Act: -0.1700

Data Index: 7876678 (Open Web Text)

Max Activating Token Index: 610

Text #4

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9976. Min Act: -0.1700

Data Index: 3636796 (Open Web Text)

Max Activating Token Index: 926

Text #5

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9863. Min Act: -0.1700

Data Index: 7151780 (Open Web Text)

Max Activating Token Index: 126

Text #6

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9983. Min Act: -0.1700

Data Index: 4855731 (Open Web Text)

Max Activating Token Index: 600

Text #7

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9725. Min Act: -0.1700

Data Index: 8701291 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9893. Min Act: -0.1700

Data Index: 1668523 (Open Web Text)

Max Activating Token Index: 456

Text #9

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9698. Min Act: -0.1700

Data Index: 165912 (Open Web Text)

Max Activating Token Index: 857

Text #10

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9593. Min Act: -0.1700

Data Index: 720637 (Open Web Text)

Max Activating Token Index: 775

Text #11

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9772. Min Act: -0.1700

Data Index: 4172101 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9374. Min Act: -0.1700

Data Index: 4597476 (Open Web Text)

Max Activating Token Index: 962

Text #13

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9535. Min Act: -0.1700

Data Index: 5915821 (Open Web Text)

Max Activating Token Index: 996

Text #14

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9661. Min Act: -0.1700

Data Index: 6735260 (Open Web Text)

Max Activating Token Index: 327

Text #15

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9455. Min Act: -0.1700

Data Index: 1888004 (Open Web Text)

Max Activating Token Index: 42

Text #16

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9461. Min Act: -0.1700

Data Index: 8270508 (Open Web Text)

Max Activating Token Index: 184

Text #17

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9332. Min Act: -0.1700

Data Index: 3214112 (Open Web Text)

Max Activating Token Index: 225

Text #18

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9503. Min Act: -0.1700

Data Index: 6101811 (Open Web Text)

Max Activating Token Index: 479

Text #19

Max Range: 3.0333. Min Range: -3.0333

Max Act: 2.9241. Min Act: -0.1700

Data Index: 4224566 (Open Web Text)

Max Activating Token Index: 563