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

Dataset: Open Web Text

Neuron 1864 in Layer 2

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: 4.4245. Min Range: -4.4245

Max Act: 4.4245. Min Act: -0.1700

Data Index: 2227989 (Open Web Text)

Max Activating Token Index: 681

Text #1

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.3859. Min Act: -0.1700

Data Index: 2365422 (Open Web Text)

Max Activating Token Index: 441

Text #2

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.3171. Min Act: -0.1700

Data Index: 1327783 (Open Web Text)

Max Activating Token Index: 288

Text #3

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2957. Min Act: -0.1700

Data Index: 7411221 (Open Web Text)

Max Activating Token Index: 595

Text #4

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2947. Min Act: -0.1700

Data Index: 4408147 (Open Web Text)

Max Activating Token Index: 323

Text #5

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2902. Min Act: -0.1700

Data Index: 3649646 (Open Web Text)

Max Activating Token Index: 65

Text #6

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.3453. Min Act: -0.1700

Data Index: 4884388 (Open Web Text)

Max Activating Token Index: 997

Text #7

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2978. Min Act: -0.1700

Data Index: 4898870 (Open Web Text)

Max Activating Token Index: 852

Text #8

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.3036. Min Act: -0.1700

Data Index: 6763953 (Open Web Text)

Max Activating Token Index: 352

Text #9

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2895. Min Act: -0.1700

Data Index: 5622193 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2586. Min Act: -0.1700

Data Index: 1009017 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.3069. Min Act: -0.1700

Data Index: 3295035 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.3121. Min Act: -0.1700

Data Index: 6608441 (Open Web Text)

Max Activating Token Index: 553

Text #13

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2572. Min Act: -0.1700

Data Index: 2448304 (Open Web Text)

Max Activating Token Index: 787

Text #14

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2705. Min Act: -0.1700

Data Index: 5701117 (Open Web Text)

Max Activating Token Index: 992

Text #15

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2705. Min Act: -0.1700

Data Index: 5502098 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2304. Min Act: -0.1700

Data Index: 4747126 (Open Web Text)

Max Activating Token Index: 532

Text #17

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2771. Min Act: -0.1700

Data Index: 902856 (Open Web Text)

Max Activating Token Index: 289

Text #18

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2230. Min Act: -0.1700

Data Index: 1060872 (Open Web Text)

Max Activating Token Index: 953

Text #19

Max Range: 4.4245. Min Range: -4.4245

Max Act: 4.2797. Min Act: -0.1700

Data Index: 4121165 (Open Web Text)

Max Activating Token Index: 507