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

Dataset: Open Web Text

Neuron 795 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: 2.8763. Min Range: -2.8763

Max Act: 2.8758. Min Act: -0.1700

Data Index: 3843206 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8763. Min Act: -0.1700

Data Index: 2436344 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8720. Min Act: -0.1700

Data Index: 2629651 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8556. Min Act: -0.1700

Data Index: 3767991 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8311. Min Act: -0.1700

Data Index: 4065663 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8331. Min Act: -0.1700

Data Index: 2957461 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8227. Min Act: -0.1700

Data Index: 3390301 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8244. Min Act: -0.1700

Data Index: 4338975 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8223. Min Act: -0.1700

Data Index: 5556498 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8040. Min Act: -0.1700

Data Index: 1698397 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8084. Min Act: -0.1700

Data Index: 1036164 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8125. Min Act: -0.1700

Data Index: 6745290 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.8127. Min Act: -0.1700

Data Index: 3599819 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.7916. Min Act: -0.1700

Data Index: 6368891 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.7868. Min Act: -0.1700

Data Index: 3701094 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.7802. Min Act: -0.1700

Data Index: 373637 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.7713. Min Act: -0.1700

Data Index: 6823643 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.7802. Min Act: -0.1700

Data Index: 3465293 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.7802. Min Act: -0.1700

Data Index: 4031553 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.8763. Min Range: -2.8763

Max Act: 2.7598. Min Act: -0.1700

Data Index: 3020474 (Open Web Text)

Max Activating Token Index: 1