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

Dataset: Open Web Text

Neuron 1745 in Layer 1

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: 0.7377. Min Range: -0.7377

Max Act: 0.7377. Min Act: -0.1700

Data Index: 8728833 (Open Web Text)

Max Activating Token Index: 757

Text #1

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7271. Min Act: -0.1700

Data Index: 7274510 (Open Web Text)

Max Activating Token Index: 762

Text #2

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7159. Min Act: -0.1700

Data Index: 4981913 (Open Web Text)

Max Activating Token Index: 756

Text #3

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7177. Min Act: -0.1700

Data Index: 7420616 (Open Web Text)

Max Activating Token Index: 770

Text #4

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6989. Min Act: -0.1700

Data Index: 6478752 (Open Web Text)

Max Activating Token Index: 767

Text #5

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6982. Min Act: -0.1700

Data Index: 8728831 (Open Web Text)

Max Activating Token Index: 771

Text #6

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7062. Min Act: -0.1700

Data Index: 7770720 (Open Web Text)

Max Activating Token Index: 763

Text #7

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7034. Min Act: -0.1700

Data Index: 7579622 (Open Web Text)

Max Activating Token Index: 197

Text #8

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7019. Min Act: -0.1700

Data Index: 1784830 (Open Web Text)

Max Activating Token Index: 204

Text #9

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7045. Min Act: -0.1700

Data Index: 216802 (Open Web Text)

Max Activating Token Index: 747

Text #10

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6922. Min Act: -0.1700

Data Index: 2933684 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6946. Min Act: -0.1700

Data Index: 7318884 (Open Web Text)

Max Activating Token Index: 754

Text #12

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6970. Min Act: -0.1700

Data Index: 882596 (Open Web Text)

Max Activating Token Index: 180

Text #13

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6946. Min Act: -0.1700

Data Index: 2984381 (Open Web Text)

Max Activating Token Index: 187

Text #14

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6983. Min Act: -0.1700

Data Index: 5881759 (Open Web Text)

Max Activating Token Index: 779

Text #15

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6969. Min Act: -0.1700

Data Index: 7315329 (Open Web Text)

Max Activating Token Index: 193

Text #16

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6948. Min Act: -0.1700

Data Index: 5904901 (Open Web Text)

Max Activating Token Index: 198

Text #17

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6961. Min Act: -0.1700

Data Index: 3432956 (Open Web Text)

Max Activating Token Index: 190

Text #18

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6890. Min Act: -0.1700

Data Index: 1311540 (Open Web Text)

Max Activating Token Index: 194

Text #19

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6951. Min Act: -0.1700

Data Index: 4648854 (Open Web Text)

Max Activating Token Index: 191