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

Dataset: Open Web Text

Neuron 2945 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: 3.6188. Min Range: -3.6188

Max Act: 3.6159. Min Act: -0.1700

Data Index: 157800 (Open Web Text)

Max Activating Token Index: 150

Text #1

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.6188. Min Act: -0.1700

Data Index: 6716179 (Open Web Text)

Max Activating Token Index: 619

Text #2

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5516. Min Act: -0.1700

Data Index: 5984048 (Open Web Text)

Max Activating Token Index: 685

Text #3

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5808. Min Act: -0.1700

Data Index: 38208 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5778. Min Act: -0.1700

Data Index: 302670 (Open Web Text)

Max Activating Token Index: 148

Text #5

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5629. Min Act: -0.1700

Data Index: 7591162 (Open Web Text)

Max Activating Token Index: 152

Text #6

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5486. Min Act: -0.1700

Data Index: 2626653 (Open Web Text)

Max Activating Token Index: 102

Text #7

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5600. Min Act: -0.1700

Data Index: 642564 (Open Web Text)

Max Activating Token Index: 631

Text #8

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5532. Min Act: -0.1700

Data Index: 566440 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5333. Min Act: -0.1700

Data Index: 7913591 (Open Web Text)

Max Activating Token Index: 372

Text #10

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5280. Min Act: -0.1700

Data Index: 4895185 (Open Web Text)

Max Activating Token Index: 809

Text #11

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5086. Min Act: -0.1700

Data Index: 3965282 (Open Web Text)

Max Activating Token Index: 806

Text #12

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5201. Min Act: -0.1700

Data Index: 2443823 (Open Web Text)

Max Activating Token Index: 151

Text #13

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.4838. Min Act: -0.1700

Data Index: 521034 (Open Web Text)

Max Activating Token Index: 359

Text #14

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.4971. Min Act: -0.1700

Data Index: 4712608 (Open Web Text)

Max Activating Token Index: 310

Text #15

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5173. Min Act: -0.1700

Data Index: 5203199 (Open Web Text)

Max Activating Token Index: 235

Text #16

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.4877. Min Act: -0.1700

Data Index: 6448423 (Open Web Text)

Max Activating Token Index: 183

Text #17

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.4784. Min Act: -0.1700

Data Index: 7481832 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.4831. Min Act: -0.1700

Data Index: 2983511 (Open Web Text)

Max Activating Token Index: 703

Text #19

Max Range: 3.6188. Min Range: -3.6188

Max Act: 3.5002. Min Act: -0.1700

Data Index: 4377352 (Open Web Text)

Max Activating Token Index: 302