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

Dataset: Open Web Text

Neuron 1615 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: 4.5041. Min Range: -4.5041

Max Act: 4.5041. Min Act: -0.1700

Data Index: 968938 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.3381. Min Act: -0.1700

Data Index: 3699534 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.3097. Min Act: -0.1700

Data Index: 7090287 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2790. Min Act: -0.1700

Data Index: 3876694 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2860. Min Act: -0.1700

Data Index: 7974523 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2835. Min Act: -0.1700

Data Index: 7598257 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2825. Min Act: -0.1700

Data Index: 425485 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2832. Min Act: -0.1700

Data Index: 4891040 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2566. Min Act: -0.1700

Data Index: 838710 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2806. Min Act: -0.1700

Data Index: 3368940 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2601. Min Act: -0.1700

Data Index: 3391776 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2479. Min Act: -0.1700

Data Index: 7449736 (Open Web Text)

Max Activating Token Index: 131

Text #12

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2559. Min Act: -0.1700

Data Index: 3456145 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2721. Min Act: -0.1700

Data Index: 2724603 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2549. Min Act: -0.1700

Data Index: 8296107 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2227. Min Act: -0.1700

Data Index: 5600544 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2234. Min Act: -0.1700

Data Index: 7343097 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2198. Min Act: -0.1700

Data Index: 2439795 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2189. Min Act: -0.1700

Data Index: 2906302 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.2408. Min Act: -0.1700

Data Index: 455098 (Open Web Text)

Max Activating Token Index: 3