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

Dataset: Open Web Text

Neuron 2371 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: 4.0228. Min Range: -4.0228

Max Act: 4.0228. Min Act: -0.1700

Data Index: 7516122 (Open Web Text)

Max Activating Token Index: 684

Text #1

Max Range: 4.0228. Min Range: -4.0228

Max Act: 4.0049. Min Act: -0.1700

Data Index: 1500753 (Open Web Text)

Max Activating Token Index: 142

Text #2

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.9576. Min Act: -0.1700

Data Index: 1127346 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.9529. Min Act: -0.1700

Data Index: 1145921 (Open Web Text)

Max Activating Token Index: 624

Text #4

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.9379. Min Act: -0.1700

Data Index: 8254840 (Open Web Text)

Max Activating Token Index: 419

Text #5

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.9383. Min Act: -0.1700

Data Index: 7577736 (Open Web Text)

Max Activating Token Index: 655

Text #6

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.9030. Min Act: -0.1700

Data Index: 8303317 (Open Web Text)

Max Activating Token Index: 440

Text #7

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.9262. Min Act: -0.1700

Data Index: 1950422 (Open Web Text)

Max Activating Token Index: 257

Text #8

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.9219. Min Act: -0.1700

Data Index: 3157661 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.8742. Min Act: -0.1700

Data Index: 8186855 (Open Web Text)

Max Activating Token Index: 105

Text #10

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.8836. Min Act: -0.1700

Data Index: 2058988 (Open Web Text)

Max Activating Token Index: 135

Text #11

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.8703. Min Act: -0.1700

Data Index: 5795938 (Open Web Text)

Max Activating Token Index: 412

Text #12

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.8670. Min Act: -0.1700

Data Index: 65591 (Open Web Text)

Max Activating Token Index: 441

Text #13

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.8455. Min Act: -0.1700

Data Index: 750186 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.8623. Min Act: -0.1700

Data Index: 779421 (Open Web Text)

Max Activating Token Index: 323

Text #15

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.8447. Min Act: -0.1700

Data Index: 822460 (Open Web Text)

Max Activating Token Index: 282

Text #16

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.8465. Min Act: -0.1700

Data Index: 2944553 (Open Web Text)

Max Activating Token Index: 190

Text #17

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.8562. Min Act: -0.1700

Data Index: 4062754 (Open Web Text)

Max Activating Token Index: 288

Text #18

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.8351. Min Act: -0.1700

Data Index: 4677881 (Open Web Text)

Max Activating Token Index: 202

Text #19

Max Range: 4.0228. Min Range: -4.0228

Max Act: 3.8511. Min Act: -0.1700

Data Index: 3244332 (Open Web Text)

Max Activating Token Index: 662