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

Dataset: Open Web Text

Neuron 2231 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: 3.0443. Min Range: -3.0443

Max Act: 3.0443. Min Act: -0.1700

Data Index: 246755 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9806. Min Act: -0.1700

Data Index: 4381000 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9674. Min Act: -0.1700

Data Index: 1191537 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9702. Min Act: -0.1700

Data Index: 5200221 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9462. Min Act: -0.1700

Data Index: 7393425 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9549. Min Act: -0.1700

Data Index: 4303733 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9248. Min Act: -0.1700

Data Index: 4754140 (Open Web Text)

Max Activating Token Index: 268

Text #7

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9191. Min Act: -0.1700

Data Index: 2069954 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9230. Min Act: -0.1700

Data Index: 7140937 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9161. Min Act: -0.1700

Data Index: 3015212 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9083. Min Act: -0.1700

Data Index: 8067061 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9092. Min Act: -0.1700

Data Index: 5645981 (Open Web Text)

Max Activating Token Index: 42

Text #12

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.9161. Min Act: -0.1700

Data Index: 64652 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.8840. Min Act: -0.1700

Data Index: 2321486 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.8941. Min Act: -0.1700

Data Index: 7495663 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.8864. Min Act: -0.1700

Data Index: 1373736 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.8730. Min Act: -0.1700

Data Index: 6577502 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.8661. Min Act: -0.1700

Data Index: 8536343 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.8820. Min Act: -0.1700

Data Index: 1073455 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.0443. Min Range: -3.0443

Max Act: 2.8592. Min Act: -0.1700

Data Index: 5641686 (Open Web Text)

Max Activating Token Index: 2