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

Dataset: Open Web Text

Neuron 307 in Layer 5

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: 5.4073. Min Range: -5.4073

Max Act: 5.4073. Min Act: -0.1700

Data Index: 3760947 (Open Web Text)

Max Activating Token Index: 268

Text #1

Max Range: 5.4073. Min Range: -5.4073

Max Act: 5.2883. Min Act: -0.1700

Data Index: 3182144 (Open Web Text)

Max Activating Token Index: 267

Text #2

Max Range: 5.4073. Min Range: -5.4073

Max Act: 5.2380. Min Act: -0.1700

Data Index: 4027238 (Open Web Text)

Max Activating Token Index: 618

Text #3

Max Range: 5.4073. Min Range: -5.4073

Max Act: 5.1773. Min Act: -0.1700

Data Index: 4528446 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 5.4073. Min Range: -5.4073

Max Act: 5.1088. Min Act: -0.1700

Data Index: 5912534 (Open Web Text)

Max Activating Token Index: 217

Text #5

Max Range: 5.4073. Min Range: -5.4073

Max Act: 5.1022. Min Act: -0.1700

Data Index: 5775798 (Open Web Text)

Max Activating Token Index: 1001

Text #6

Max Range: 5.4073. Min Range: -5.4073

Max Act: 5.0688. Min Act: -0.1700

Data Index: 2894237 (Open Web Text)

Max Activating Token Index: 956

Text #7

Max Range: 5.4073. Min Range: -5.4073

Max Act: 5.0328. Min Act: -0.1700

Data Index: 6004466 (Open Web Text)

Max Activating Token Index: 803

Text #8

Max Range: 5.4073. Min Range: -5.4073

Max Act: 5.0160. Min Act: -0.1700

Data Index: 6612872 (Open Web Text)

Max Activating Token Index: 801

Text #9

Max Range: 5.4073. Min Range: -5.4073

Max Act: 4.9846. Min Act: -0.1700

Data Index: 1937043 (Open Web Text)

Max Activating Token Index: 105

Text #10

Max Range: 5.4073. Min Range: -5.4073

Max Act: 4.9886. Min Act: -0.1700

Data Index: 4767677 (Open Web Text)

Max Activating Token Index: 511

Text #11

Max Range: 5.4073. Min Range: -5.4073

Max Act: 4.9746. Min Act: -0.1700

Data Index: 1995656 (Open Web Text)

Max Activating Token Index: 199

Text #12

Max Range: 5.4073. Min Range: -5.4073

Max Act: 4.9853. Min Act: -0.1700

Data Index: 7481724 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 5.4073. Min Range: -5.4073

Max Act: 4.9653. Min Act: -0.1700

Data Index: 3959873 (Open Web Text)

Max Activating Token Index: 1013

Text #14

Max Range: 5.4073. Min Range: -5.4073

Max Act: 4.9239. Min Act: -0.1700

Data Index: 7653530 (Open Web Text)

Max Activating Token Index: 584

Text #15

Max Range: 5.4073. Min Range: -5.4073

Max Act: 4.9733. Min Act: -0.1700

Data Index: 3716557 (Open Web Text)

Max Activating Token Index: 254

Text #16

Max Range: 5.4073. Min Range: -5.4073

Max Act: 4.9392. Min Act: -0.1700

Data Index: 663811 (Open Web Text)

Max Activating Token Index: 681

Text #17

Max Range: 5.4073. Min Range: -5.4073

Max Act: 4.8952. Min Act: -0.1700

Data Index: 7490461 (Open Web Text)

Max Activating Token Index: 967

Text #18

Max Range: 5.4073. Min Range: -5.4073

Max Act: 4.9086. Min Act: -0.1700

Data Index: 2983937 (Open Web Text)

Max Activating Token Index: 266

Text #19

Max Range: 5.4073. Min Range: -5.4073

Max Act: 4.8984. Min Act: -0.1700

Data Index: 6630781 (Open Web Text)

Max Activating Token Index: 66