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

Dataset: Open Web Text

Neuron 673 in Layer 6

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: 3.6273. Min Range: -3.6273

Max Act: 3.6273. Min Act: -0.1700

Data Index: 1840134 (Open Web Text)

Max Activating Token Index: 469

Text #1

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.5384. Min Act: -0.1700

Data Index: 6691462 (Open Web Text)

Max Activating Token Index: 326

Text #2

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.5434. Min Act: -0.1700

Data Index: 2520485 (Open Web Text)

Max Activating Token Index: 957

Text #3

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.5110. Min Act: -0.1700

Data Index: 8758635 (Open Web Text)

Max Activating Token Index: 480

Text #4

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4978. Min Act: -0.1700

Data Index: 8368645 (Open Web Text)

Max Activating Token Index: 995

Text #5

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.5034. Min Act: -0.1700

Data Index: 679621 (Open Web Text)

Max Activating Token Index: 355

Text #6

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.5022. Min Act: -0.1700

Data Index: 3069806 (Open Web Text)

Max Activating Token Index: 392

Text #7

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4851. Min Act: -0.1700

Data Index: 3274238 (Open Web Text)

Max Activating Token Index: 207

Text #8

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4634. Min Act: -0.1700

Data Index: 4951076 (Open Web Text)

Max Activating Token Index: 1015

Text #9

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4548. Min Act: -0.1700

Data Index: 2197805 (Open Web Text)

Max Activating Token Index: 473

Text #10

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4459. Min Act: -0.1700

Data Index: 1118097 (Open Web Text)

Max Activating Token Index: 61

Text #11

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4576. Min Act: -0.1700

Data Index: 6623070 (Open Web Text)

Max Activating Token Index: 438

Text #12

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4411. Min Act: -0.1700

Data Index: 2701540 (Open Web Text)

Max Activating Token Index: 281

Text #13

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4495. Min Act: -0.1700

Data Index: 6344977 (Open Web Text)

Max Activating Token Index: 422

Text #14

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4389. Min Act: -0.1700

Data Index: 3282652 (Open Web Text)

Max Activating Token Index: 340

Text #15

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4378. Min Act: -0.1700

Data Index: 4599510 (Open Web Text)

Max Activating Token Index: 219

Text #16

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4385. Min Act: -0.1700

Data Index: 6748268 (Open Web Text)

Max Activating Token Index: 719

Text #17

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4276. Min Act: -0.1700

Data Index: 1580360 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4260. Min Act: -0.1700

Data Index: 8623725 (Open Web Text)

Max Activating Token Index: 516

Text #19

Max Range: 3.6273. Min Range: -3.6273

Max Act: 3.4358. Min Act: -0.1700

Data Index: 1185390 (Open Web Text)

Max Activating Token Index: 1023