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

Dataset: Open Web Text

Neuron 2014 in Layer 4

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: 3.9489. Min Range: -3.9489

Max Act: 3.9489. Min Act: -0.1700

Data Index: 7667203 (Open Web Text)

Max Activating Token Index: 409

Text #1

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.8850. Min Act: -0.1700

Data Index: 5221615 (Open Web Text)

Max Activating Token Index: 810

Text #2

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.7674. Min Act: -0.1700

Data Index: 6105185 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.8009. Min Act: -0.1700

Data Index: 8183644 (Open Web Text)

Max Activating Token Index: 311

Text #4

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.7706. Min Act: -0.1700

Data Index: 1365712 (Open Web Text)

Max Activating Token Index: 540

Text #5

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.8029. Min Act: -0.1700

Data Index: 5096980 (Open Web Text)

Max Activating Token Index: 763

Text #6

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.7595. Min Act: -0.1700

Data Index: 4727751 (Open Web Text)

Max Activating Token Index: 732

Text #7

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.7500. Min Act: -0.1700

Data Index: 4868242 (Open Web Text)

Max Activating Token Index: 339

Text #8

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.7471. Min Act: -0.1700

Data Index: 2037759 (Open Web Text)

Max Activating Token Index: 319

Text #9

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.7366. Min Act: -0.1700

Data Index: 7552006 (Open Web Text)

Max Activating Token Index: 544

Text #10

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.7213. Min Act: -0.1700

Data Index: 3964944 (Open Web Text)

Max Activating Token Index: 666

Text #11

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.7183. Min Act: -0.1700

Data Index: 8337092 (Open Web Text)

Max Activating Token Index: 899

Text #12

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.6707. Min Act: -0.1700

Data Index: 4641714 (Open Web Text)

Max Activating Token Index: 592

Text #13

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.7247. Min Act: -0.1700

Data Index: 2537626 (Open Web Text)

Max Activating Token Index: 194

Text #14

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.7230. Min Act: -0.1700

Data Index: 8107111 (Open Web Text)

Max Activating Token Index: 437

Text #15

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.6947. Min Act: -0.1700

Data Index: 5544112 (Open Web Text)

Max Activating Token Index: 273

Text #16

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.7079. Min Act: -0.1700

Data Index: 3045915 (Open Web Text)

Max Activating Token Index: 514

Text #17

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.6996. Min Act: -0.1700

Data Index: 6209592 (Open Web Text)

Max Activating Token Index: 277

Text #18

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.6944. Min Act: -0.1700

Data Index: 8469195 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.6679. Min Act: -0.1700

Data Index: 5320769 (Open Web Text)

Max Activating Token Index: 307