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

Dataset: Open Web Text

Neuron 626 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: 1.6951. Min Range: -1.6951

Max Act: 1.6951. Min Act: -0.1700

Data Index: 3809964 (Open Web Text)

Max Activating Token Index: 327

Text #1

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6655. Min Act: -0.1700

Data Index: 1553738 (Open Web Text)

Max Activating Token Index: 243

Text #2

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6564. Min Act: -0.1700

Data Index: 67756 (Open Web Text)

Max Activating Token Index: 688

Text #3

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6411. Min Act: -0.1700

Data Index: 398664 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6391. Min Act: -0.1700

Data Index: 1491732 (Open Web Text)

Max Activating Token Index: 521

Text #5

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6331. Min Act: -0.1700

Data Index: 4058794 (Open Web Text)

Max Activating Token Index: 61

Text #6

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6251. Min Act: -0.1700

Data Index: 654817 (Open Web Text)

Max Activating Token Index: 417

Text #7

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6212. Min Act: -0.1700

Data Index: 622098 (Open Web Text)

Max Activating Token Index: 935

Text #8

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6188. Min Act: -0.1700

Data Index: 6315724 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6129. Min Act: -0.1700

Data Index: 5698715 (Open Web Text)

Max Activating Token Index: 639

Text #10

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6122. Min Act: -0.1700

Data Index: 8135637 (Open Web Text)

Max Activating Token Index: 225

Text #11

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5922. Min Act: -0.1699

Data Index: 6315736 (Open Web Text)

Max Activating Token Index: 536

Text #12

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6029. Min Act: -0.1700

Data Index: 3447031 (Open Web Text)

Max Activating Token Index: 525

Text #13

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5977. Min Act: -0.1700

Data Index: 3342726 (Open Web Text)

Max Activating Token Index: 140

Text #14

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5903. Min Act: -0.1700

Data Index: 4384652 (Open Web Text)

Max Activating Token Index: 381

Text #15

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5956. Min Act: -0.1700

Data Index: 1513920 (Open Web Text)

Max Activating Token Index: 268

Text #16

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5951. Min Act: -0.1700

Data Index: 5794430 (Open Web Text)

Max Activating Token Index: 515

Text #17

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5876. Min Act: -0.1700

Data Index: 2589319 (Open Web Text)

Max Activating Token Index: 275

Text #18

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5993. Min Act: -0.1700

Data Index: 1909428 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5869. Min Act: -0.1700

Data Index: 4294565 (Open Web Text)

Max Activating Token Index: 208