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

Dataset: Open Web Text

Neuron 652 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: 4.6930. Min Range: -4.6930

Max Act: 4.6930. Min Act: -0.1700

Data Index: 209082 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.6355. Min Act: -0.1700

Data Index: 7409109 (Open Web Text)

Max Activating Token Index: 615

Text #2

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.6612. Min Act: -0.1700

Data Index: 549793 (Open Web Text)

Max Activating Token Index: 309

Text #3

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.6595. Min Act: -0.1700

Data Index: 6771495 (Open Web Text)

Max Activating Token Index: 711

Text #4

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.5489. Min Act: -0.1700

Data Index: 7631573 (Open Web Text)

Max Activating Token Index: 201

Text #5

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.5347. Min Act: -0.1700

Data Index: 8227347 (Open Web Text)

Max Activating Token Index: 514

Text #6

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.5569. Min Act: -0.1700

Data Index: 672867 (Open Web Text)

Max Activating Token Index: 697

Text #7

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.5770. Min Act: -0.1700

Data Index: 4319663 (Open Web Text)

Max Activating Token Index: 176

Text #8

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.5558. Min Act: -0.1700

Data Index: 5940676 (Open Web Text)

Max Activating Token Index: 790

Text #9

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.5286. Min Act: -0.1700

Data Index: 3777393 (Open Web Text)

Max Activating Token Index: 899

Text #10

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.5187. Min Act: -0.1700

Data Index: 5792624 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.5431. Min Act: -0.1700

Data Index: 85964 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.5207. Min Act: -0.1700

Data Index: 6678073 (Open Web Text)

Max Activating Token Index: 614

Text #13

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.4767. Min Act: -0.1700

Data Index: 3524116 (Open Web Text)

Max Activating Token Index: 372

Text #14

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.4990. Min Act: -0.1700

Data Index: 1380981 (Open Web Text)

Max Activating Token Index: 579

Text #15

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.4739. Min Act: -0.1700

Data Index: 7397440 (Open Web Text)

Max Activating Token Index: 1007

Text #16

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.4878. Min Act: -0.1700

Data Index: 2780537 (Open Web Text)

Max Activating Token Index: 705

Text #17

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.4965. Min Act: -0.1700

Data Index: 2576485 (Open Web Text)

Max Activating Token Index: 608

Text #18

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.4870. Min Act: -0.1700

Data Index: 2525095 (Open Web Text)

Max Activating Token Index: 987

Text #19

Max Range: 4.6930. Min Range: -4.6930

Max Act: 4.4941. Min Act: -0.1700

Data Index: 3770393 (Open Web Text)

Max Activating Token Index: 739