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

Dataset: Open Web Text

Neuron 1516 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: 3.5181. Min Range: -3.5181

Max Act: 3.5181. Min Act: -0.1700

Data Index: 6441955 (Open Web Text)

Max Activating Token Index: 1001

Text #1

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.5112. Min Act: -0.1700

Data Index: 2631928 (Open Web Text)

Max Activating Token Index: 396

Text #2

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4564. Min Act: -0.1700

Data Index: 8701063 (Open Web Text)

Max Activating Token Index: 326

Text #3

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4696. Min Act: -0.1700

Data Index: 6252442 (Open Web Text)

Max Activating Token Index: 921

Text #4

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4699. Min Act: -0.1700

Data Index: 6926629 (Open Web Text)

Max Activating Token Index: 951

Text #5

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4632. Min Act: -0.1700

Data Index: 5054403 (Open Web Text)

Max Activating Token Index: 606

Text #6

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4696. Min Act: -0.1700

Data Index: 2517898 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4460. Min Act: -0.1700

Data Index: 1159189 (Open Web Text)

Max Activating Token Index: 528

Text #8

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4392. Min Act: -0.1700

Data Index: 2313578 (Open Web Text)

Max Activating Token Index: 50

Text #9

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4469. Min Act: -0.1700

Data Index: 6841211 (Open Web Text)

Max Activating Token Index: 674

Text #10

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4511. Min Act: -0.1700

Data Index: 2978069 (Open Web Text)

Max Activating Token Index: 909

Text #11

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4340. Min Act: -0.1700

Data Index: 5849902 (Open Web Text)

Max Activating Token Index: 448

Text #12

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4314. Min Act: -0.1700

Data Index: 4862218 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4369. Min Act: -0.1700

Data Index: 154512 (Open Web Text)

Max Activating Token Index: 423

Text #14

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4443. Min Act: -0.1700

Data Index: 56559 (Open Web Text)

Max Activating Token Index: 661

Text #15

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4350. Min Act: -0.1700

Data Index: 3471144 (Open Web Text)

Max Activating Token Index: 599

Text #16

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4343. Min Act: -0.1700

Data Index: 1161792 (Open Web Text)

Max Activating Token Index: 710

Text #17

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4318. Min Act: -0.1700

Data Index: 7355945 (Open Web Text)

Max Activating Token Index: 50

Text #18

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4379. Min Act: -0.1700

Data Index: 8009923 (Open Web Text)

Max Activating Token Index: 482

Text #19

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4229. Min Act: -0.1700

Data Index: 6727882 (Open Web Text)

Max Activating Token Index: 656