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

Dataset: Open Web Text

Neuron 686 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: 1.5423. Min Range: -1.5423

Max Act: 1.5423. Min Act: -0.1700

Data Index: 2456881 (Open Web Text)

Max Activating Token Index: 507

Text #1

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.5395. Min Act: -0.1700

Data Index: 3670051 (Open Web Text)

Max Activating Token Index: 170

Text #2

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.5270. Min Act: -0.1700

Data Index: 7468234 (Open Web Text)

Max Activating Token Index: 335

Text #3

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.5168. Min Act: -0.1700

Data Index: 3572803 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.5130. Min Act: -0.1699

Data Index: 1872442 (Open Web Text)

Max Activating Token Index: 90

Text #5

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.5075. Min Act: -0.1700

Data Index: 6508198 (Open Web Text)

Max Activating Token Index: 373

Text #6

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.5067. Min Act: -0.1700

Data Index: 1468255 (Open Web Text)

Max Activating Token Index: 304

Text #7

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.5049. Min Act: -0.1700

Data Index: 6690251 (Open Web Text)

Max Activating Token Index: 355

Text #8

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.5087. Min Act: -0.1700

Data Index: 5728577 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.4655. Min Act: -0.1700

Data Index: 7392220 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.4924. Min Act: -0.1700

Data Index: 5391323 (Open Web Text)

Max Activating Token Index: 37

Text #11

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.4744. Min Act: -0.1700

Data Index: 7331063 (Open Web Text)

Max Activating Token Index: 34

Text #12

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.4511. Min Act: -0.1700

Data Index: 6495890 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.4657. Min Act: -0.1700

Data Index: 4420665 (Open Web Text)

Max Activating Token Index: 265

Text #14

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.4619. Min Act: -0.1700

Data Index: 1423722 (Open Web Text)

Max Activating Token Index: 772

Text #15

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.4332. Min Act: -0.1700

Data Index: 4010873 (Open Web Text)

Max Activating Token Index: 807

Text #16

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.4456. Min Act: -0.1700

Data Index: 5929092 (Open Web Text)

Max Activating Token Index: 128

Text #17

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.4429. Min Act: -0.1700

Data Index: 1559227 (Open Web Text)

Max Activating Token Index: 532

Text #18

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.4370. Min Act: -0.1700

Data Index: 1669557 (Open Web Text)

Max Activating Token Index: 373

Text #19

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.4530. Min Act: -0.1700

Data Index: 4755907 (Open Web Text)

Max Activating Token Index: 319