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

Dataset: Open Web Text

Neuron 638 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: 1.7617. Min Range: -1.7617

Max Act: 1.7617. Min Act: -0.1700

Data Index: 2766466 (Open Web Text)

Max Activating Token Index: 625

Text #1

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.7128. Min Act: -0.1700

Data Index: 6819622 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6932. Min Act: -0.1700

Data Index: 2044153 (Open Web Text)

Max Activating Token Index: 465

Text #3

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6753. Min Act: -0.1700

Data Index: 5440084 (Open Web Text)

Max Activating Token Index: 317

Text #4

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6794. Min Act: -0.1700

Data Index: 4993958 (Open Web Text)

Max Activating Token Index: 609

Text #5

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6549. Min Act: -0.1700

Data Index: 3893275 (Open Web Text)

Max Activating Token Index: 343

Text #6

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6538. Min Act: -0.1700

Data Index: 41515 (Open Web Text)

Max Activating Token Index: 473

Text #7

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6481. Min Act: -0.1700

Data Index: 8022425 (Open Web Text)

Max Activating Token Index: 358

Text #8

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6511. Min Act: -0.1700

Data Index: 6633030 (Open Web Text)

Max Activating Token Index: 259

Text #9

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6573. Min Act: -0.1700

Data Index: 3115435 (Open Web Text)

Max Activating Token Index: 312

Text #10

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6291. Min Act: -0.1700

Data Index: 4441664 (Open Web Text)

Max Activating Token Index: 617

Text #11

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6302. Min Act: -0.1700

Data Index: 8748467 (Open Web Text)

Max Activating Token Index: 346

Text #12

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6237. Min Act: -0.1700

Data Index: 4313593 (Open Web Text)

Max Activating Token Index: 786

Text #13

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6283. Min Act: -0.1700

Data Index: 1319843 (Open Web Text)

Max Activating Token Index: 320

Text #14

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6244. Min Act: -0.1700

Data Index: 1617359 (Open Web Text)

Max Activating Token Index: 819

Text #15

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6318. Min Act: -0.1700

Data Index: 3819663 (Open Web Text)

Max Activating Token Index: 393

Text #16

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6247. Min Act: -0.1700

Data Index: 8319587 (Open Web Text)

Max Activating Token Index: 220

Text #17

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6233. Min Act: -0.1700

Data Index: 7833183 (Open Web Text)

Max Activating Token Index: 99

Text #18

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6258. Min Act: -0.1700

Data Index: 6310266 (Open Web Text)

Max Activating Token Index: 464

Text #19

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.6087. Min Act: -0.1700

Data Index: 699181 (Open Web Text)

Max Activating Token Index: 555