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

Dataset: Open Web Text

Neuron 365 in Layer 3

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: 3.5405. Min Range: -3.5405

Max Act: 3.5405. Min Act: -0.1700

Data Index: 8807757 (Open Web Text)

Max Activating Token Index: 862

Text #1

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.5314. Min Act: -0.1700

Data Index: 6402827 (Open Web Text)

Max Activating Token Index: 595

Text #2

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4764. Min Act: -0.1700

Data Index: 1230082 (Open Web Text)

Max Activating Token Index: 633

Text #3

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4130. Min Act: -0.1700

Data Index: 7243797 (Open Web Text)

Max Activating Token Index: 19

Text #4

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4241. Min Act: -0.1700

Data Index: 8193622 (Open Web Text)

Max Activating Token Index: 552

Text #5

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4366. Min Act: -0.1700

Data Index: 1235227 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4098. Min Act: -0.1700

Data Index: 6237804 (Open Web Text)

Max Activating Token Index: 802

Text #7

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4201. Min Act: -0.1700

Data Index: 7243795 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3821. Min Act: -0.1700

Data Index: 2849690 (Open Web Text)

Max Activating Token Index: 592

Text #9

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4042. Min Act: -0.1700

Data Index: 4638220 (Open Web Text)

Max Activating Token Index: 547

Text #10

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3766. Min Act: -0.1700

Data Index: 4147093 (Open Web Text)

Max Activating Token Index: 883

Text #11

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3066. Min Act: -0.1700

Data Index: 7263769 (Open Web Text)

Max Activating Token Index: 755

Text #12

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3453. Min Act: -0.1700

Data Index: 7234595 (Open Web Text)

Max Activating Token Index: 452

Text #13

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3457. Min Act: -0.1700

Data Index: 7041621 (Open Web Text)

Max Activating Token Index: 231

Text #14

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3066. Min Act: -0.1700

Data Index: 6420969 (Open Web Text)

Max Activating Token Index: 530

Text #15

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3021. Min Act: -0.1700

Data Index: 1793411 (Open Web Text)

Max Activating Token Index: 143

Text #16

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3129. Min Act: -0.1700

Data Index: 7815145 (Open Web Text)

Max Activating Token Index: 196

Text #17

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3233. Min Act: -0.1700

Data Index: 4227842 (Open Web Text)

Max Activating Token Index: 659

Text #18

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3246. Min Act: -0.1700

Data Index: 6477129 (Open Web Text)

Max Activating Token Index: 524

Text #19

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.2924. Min Act: -0.1700

Data Index: 905807 (Open Web Text)

Max Activating Token Index: 575