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

Dataset: Open Web Text

Neuron 2981 in Layer 4

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: 3.5765. Min Range: -3.5765

Max Act: 3.5765. Min Act: -0.1700

Data Index: 3402944 (Open Web Text)

Max Activating Token Index: 659

Text #1

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.5398. Min Act: -0.1700

Data Index: 6779646 (Open Web Text)

Max Activating Token Index: 814

Text #2

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.5630. Min Act: -0.1700

Data Index: 1380939 (Open Web Text)

Max Activating Token Index: 746

Text #3

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.5070. Min Act: -0.1700

Data Index: 4745361 (Open Web Text)

Max Activating Token Index: 221

Text #4

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.5109. Min Act: -0.1700

Data Index: 7638644 (Open Web Text)

Max Activating Token Index: 533

Text #5

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.5098. Min Act: -0.1700

Data Index: 6046792 (Open Web Text)

Max Activating Token Index: 1013

Text #6

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.5305. Min Act: -0.1700

Data Index: 6002924 (Open Web Text)

Max Activating Token Index: 355

Text #7

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4760. Min Act: -0.1700

Data Index: 8383906 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4972. Min Act: -0.1700

Data Index: 3813942 (Open Web Text)

Max Activating Token Index: 452

Text #9

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4970. Min Act: -0.1700

Data Index: 4170123 (Open Web Text)

Max Activating Token Index: 385

Text #10

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.5137. Min Act: -0.1700

Data Index: 5080850 (Open Web Text)

Max Activating Token Index: 457

Text #11

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4902. Min Act: -0.1700

Data Index: 3692623 (Open Web Text)

Max Activating Token Index: 738

Text #12

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4806. Min Act: -0.1700

Data Index: 5034373 (Open Web Text)

Max Activating Token Index: 421

Text #13

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4646. Min Act: -0.1700

Data Index: 8029054 (Open Web Text)

Max Activating Token Index: 283

Text #14

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4885. Min Act: -0.1700

Data Index: 965726 (Open Web Text)

Max Activating Token Index: 440

Text #15

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4447. Min Act: -0.1700

Data Index: 6908645 (Open Web Text)

Max Activating Token Index: 77

Text #16

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4515. Min Act: -0.1700

Data Index: 6500503 (Open Web Text)

Max Activating Token Index: 95

Text #17

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4418. Min Act: -0.1700

Data Index: 68765 (Open Web Text)

Max Activating Token Index: 255

Text #18

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4527. Min Act: -0.1700

Data Index: 6046797 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 3.5765. Min Range: -3.5765

Max Act: 3.4615. Min Act: -0.1700

Data Index: 3421766 (Open Web Text)

Max Activating Token Index: 389