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

Dataset: Open Web Text

Neuron 381 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: 4.5367. Min Range: -4.5367

Max Act: 4.5367. Min Act: -0.1700

Data Index: 8346846 (Open Web Text)

Max Activating Token Index: 670

Text #1

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4843. Min Act: -0.1700

Data Index: 4960461 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4950. Min Act: -0.1700

Data Index: 3613026 (Open Web Text)

Max Activating Token Index: 789

Text #3

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4996. Min Act: -0.1700

Data Index: 7922525 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4654. Min Act: -0.1700

Data Index: 6040138 (Open Web Text)

Max Activating Token Index: 292

Text #5

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4736. Min Act: -0.1700

Data Index: 2634395 (Open Web Text)

Max Activating Token Index: 229

Text #6

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4815. Min Act: -0.1700

Data Index: 7937307 (Open Web Text)

Max Activating Token Index: 562

Text #7

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4853. Min Act: -0.1700

Data Index: 491394 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4472. Min Act: -0.1700

Data Index: 7876028 (Open Web Text)

Max Activating Token Index: 387

Text #9

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4223. Min Act: -0.1700

Data Index: 4054384 (Open Web Text)

Max Activating Token Index: 420

Text #10

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4454. Min Act: -0.1700

Data Index: 3861689 (Open Web Text)

Max Activating Token Index: 600

Text #11

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4431. Min Act: -0.1700

Data Index: 628858 (Open Web Text)

Max Activating Token Index: 426

Text #12

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4417. Min Act: -0.1700

Data Index: 1664215 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4533. Min Act: -0.1700

Data Index: 4432343 (Open Web Text)

Max Activating Token Index: 243

Text #14

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4364. Min Act: -0.1700

Data Index: 6311779 (Open Web Text)

Max Activating Token Index: 467

Text #15

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4535. Min Act: -0.1700

Data Index: 2663094 (Open Web Text)

Max Activating Token Index: 216

Text #16

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4511. Min Act: -0.1700

Data Index: 6052414 (Open Web Text)

Max Activating Token Index: 300

Text #17

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4319. Min Act: -0.1700

Data Index: 452198 (Open Web Text)

Max Activating Token Index: 604

Text #18

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4253. Min Act: -0.1700

Data Index: 2024217 (Open Web Text)

Max Activating Token Index: 270

Text #19

Max Range: 4.5367. Min Range: -4.5367

Max Act: 4.4465. Min Act: -0.1700

Data Index: 4449796 (Open Web Text)

Max Activating Token Index: 562