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

Dataset: Open Web Text

Neuron 880 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: 6.0388. Min Range: -6.0388

Max Act: 6.0388. Min Act: -0.1700

Data Index: 2342333 (Open Web Text)

Max Activating Token Index: 482

Text #1

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.9781. Min Act: -0.1700

Data Index: 1759222 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8867. Min Act: -0.1700

Data Index: 5551501 (Open Web Text)

Max Activating Token Index: 292

Text #3

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8833. Min Act: -0.1700

Data Index: 2467597 (Open Web Text)

Max Activating Token Index: 899

Text #4

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8976. Min Act: -0.1700

Data Index: 139568 (Open Web Text)

Max Activating Token Index: 500

Text #5

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.9333. Min Act: -0.1700

Data Index: 7636705 (Open Web Text)

Max Activating Token Index: 160

Text #6

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8895. Min Act: -0.1700

Data Index: 2883436 (Open Web Text)

Max Activating Token Index: 607

Text #7

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8485. Min Act: -0.1700

Data Index: 5889511 (Open Web Text)

Max Activating Token Index: 906

Text #8

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.9068. Min Act: -0.1700

Data Index: 4224430 (Open Web Text)

Max Activating Token Index: 312

Text #9

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8986. Min Act: -0.1700

Data Index: 2260252 (Open Web Text)

Max Activating Token Index: 401

Text #10

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8569. Min Act: -0.1700

Data Index: 7231964 (Open Web Text)

Max Activating Token Index: 408

Text #11

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8708. Min Act: -0.1700

Data Index: 4207288 (Open Web Text)

Max Activating Token Index: 486

Text #12

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8470. Min Act: -0.1700

Data Index: 3086064 (Open Web Text)

Max Activating Token Index: 415

Text #13

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8127. Min Act: -0.1700

Data Index: 5107174 (Open Web Text)

Max Activating Token Index: 545

Text #14

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8862. Min Act: -0.1700

Data Index: 4156380 (Open Web Text)

Max Activating Token Index: 87

Text #15

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8580. Min Act: -0.1700

Data Index: 5596730 (Open Web Text)

Max Activating Token Index: 520

Text #16

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.7617. Min Act: -0.1700

Data Index: 5813202 (Open Web Text)

Max Activating Token Index: 960

Text #17

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8890. Min Act: -0.1700

Data Index: 3334889 (Open Web Text)

Max Activating Token Index: 313

Text #18

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8608. Min Act: -0.1700

Data Index: 3656306 (Open Web Text)

Max Activating Token Index: 380

Text #19

Max Range: 6.0388. Min Range: -6.0388

Max Act: 5.8936. Min Act: -0.1700

Data Index: 6185037 (Open Web Text)

Max Activating Token Index: 496