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

Dataset: Open Web Text

Neuron 2818 in Layer 6

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: 4.0879. Min Range: -4.0879

Max Act: 4.0879. Min Act: -0.1700

Data Index: 1737111 (Open Web Text)

Max Activating Token Index: 792

Text #1

Max Range: 4.0879. Min Range: -4.0879

Max Act: 4.0183. Min Act: -0.1700

Data Index: 6596049 (Open Web Text)

Max Activating Token Index: 852

Text #2

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9515. Min Act: -0.1700

Data Index: 3488511 (Open Web Text)

Max Activating Token Index: 575

Text #3

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9275. Min Act: -0.1700

Data Index: 1513964 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9144. Min Act: -0.1700

Data Index: 2314340 (Open Web Text)

Max Activating Token Index: 754

Text #5

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9139. Min Act: -0.1700

Data Index: 1909714 (Open Web Text)

Max Activating Token Index: 90

Text #6

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.8819. Min Act: -0.1700

Data Index: 479003 (Open Web Text)

Max Activating Token Index: 652

Text #7

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.8985. Min Act: -0.1700

Data Index: 6332155 (Open Web Text)

Max Activating Token Index: 118

Text #8

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.8301. Min Act: -0.1700

Data Index: 2129822 (Open Web Text)

Max Activating Token Index: 789

Text #9

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.8328. Min Act: -0.1700

Data Index: 2166812 (Open Web Text)

Max Activating Token Index: 907

Text #10

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.8369. Min Act: -0.1700

Data Index: 3235399 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.8273. Min Act: -0.1700

Data Index: 3951864 (Open Web Text)

Max Activating Token Index: 906

Text #12

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.8042. Min Act: -0.1700

Data Index: 4688997 (Open Web Text)

Max Activating Token Index: 558

Text #13

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.8026. Min Act: -0.1700

Data Index: 4112156 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.7951. Min Act: -0.1700

Data Index: 7553671 (Open Web Text)

Max Activating Token Index: 557

Text #15

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.7404. Min Act: -0.1700

Data Index: 5432791 (Open Web Text)

Max Activating Token Index: 609

Text #16

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.7483. Min Act: -0.1700

Data Index: 549035 (Open Web Text)

Max Activating Token Index: 184

Text #17

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.7457. Min Act: -0.1700

Data Index: 1899587 (Open Web Text)

Max Activating Token Index: 500

Text #18

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.7644. Min Act: -0.1700

Data Index: 4718606 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.7203. Min Act: -0.1700

Data Index: 5550571 (Open Web Text)

Max Activating Token Index: 311