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

Dataset: Open Web Text

Neuron 998 in Layer 5

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: 4.9395. Min Range: -4.9395

Max Act: 4.9034. Min Act: -0.1700

Data Index: 4470622 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.9395. Min Act: -0.1700

Data Index: 4400428 (Open Web Text)

Max Activating Token Index: 418

Text #2

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8798. Min Act: -0.1700

Data Index: 5564311 (Open Web Text)

Max Activating Token Index: 240

Text #3

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8980. Min Act: -0.1700

Data Index: 4855358 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8844. Min Act: -0.1700

Data Index: 3601410 (Open Web Text)

Max Activating Token Index: 88

Text #5

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8980. Min Act: -0.1700

Data Index: 255025 (Open Web Text)

Max Activating Token Index: 613

Text #6

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8660. Min Act: -0.1700

Data Index: 6745316 (Open Web Text)

Max Activating Token Index: 806

Text #7

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8573. Min Act: -0.1700

Data Index: 436762 (Open Web Text)

Max Activating Token Index: 378

Text #8

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8349. Min Act: -0.1700

Data Index: 5829476 (Open Web Text)

Max Activating Token Index: 754

Text #9

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8511. Min Act: -0.1700

Data Index: 8536856 (Open Web Text)

Max Activating Token Index: 617

Text #10

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8372. Min Act: -0.1700

Data Index: 1533840 (Open Web Text)

Max Activating Token Index: 33

Text #11

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8251. Min Act: -0.1700

Data Index: 993026 (Open Web Text)

Max Activating Token Index: 793

Text #12

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8495. Min Act: -0.1700

Data Index: 8312518 (Open Web Text)

Max Activating Token Index: 524

Text #13

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8626. Min Act: -0.1700

Data Index: 7000348 (Open Web Text)

Max Activating Token Index: 803

Text #14

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8271. Min Act: -0.1700

Data Index: 164317 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8050. Min Act: -0.1700

Data Index: 4517717 (Open Web Text)

Max Activating Token Index: 614

Text #16

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.7835. Min Act: -0.1700

Data Index: 4526226 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8154. Min Act: -0.1700

Data Index: 237251 (Open Web Text)

Max Activating Token Index: 29

Text #18

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8251. Min Act: -0.1700

Data Index: 2936176 (Open Web Text)

Max Activating Token Index: 513

Text #19

Max Range: 4.9395. Min Range: -4.9395

Max Act: 4.8028. Min Act: -0.1700

Data Index: 3238937 (Open Web Text)

Max Activating Token Index: 414