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

Dataset: Open Web Text

Neuron 2708 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: 3.0039. Min Range: -3.0039

Max Act: 3.0039. Min Act: -0.1700

Data Index: 2591127 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9649. Min Act: -0.1700

Data Index: 3147446 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9642. Min Act: -0.1700

Data Index: 4666 (Open Web Text)

Max Activating Token Index: 318

Text #3

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9323. Min Act: -0.1700

Data Index: 6337996 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9286. Min Act: -0.1700

Data Index: 6085698 (Open Web Text)

Max Activating Token Index: 419

Text #5

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9286. Min Act: -0.1700

Data Index: 2591120 (Open Web Text)

Max Activating Token Index: 100

Text #6

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9046. Min Act: -0.1700

Data Index: 1133389 (Open Web Text)

Max Activating Token Index: 572

Text #7

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8998. Min Act: -0.1700

Data Index: 8732310 (Open Web Text)

Max Activating Token Index: 640

Text #8

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8879. Min Act: -0.1700

Data Index: 3184111 (Open Web Text)

Max Activating Token Index: 337

Text #9

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8805. Min Act: -0.1700

Data Index: 1011980 (Open Web Text)

Max Activating Token Index: 174

Text #10

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8843. Min Act: -0.1700

Data Index: 44492 (Open Web Text)

Max Activating Token Index: 652

Text #11

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8691. Min Act: -0.1700

Data Index: 6374699 (Open Web Text)

Max Activating Token Index: 869

Text #12

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8672. Min Act: -0.1700

Data Index: 2459958 (Open Web Text)

Max Activating Token Index: 437

Text #13

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8604. Min Act: -0.1700

Data Index: 4664 (Open Web Text)

Max Activating Token Index: 867

Text #14

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8579. Min Act: -0.1700

Data Index: 3745214 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8619. Min Act: -0.1700

Data Index: 6950722 (Open Web Text)

Max Activating Token Index: 144

Text #16

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8397. Min Act: -0.1700

Data Index: 2936558 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8255. Min Act: -0.1700

Data Index: 4601991 (Open Web Text)

Max Activating Token Index: 224

Text #18

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8248. Min Act: -0.1700

Data Index: 3801996 (Open Web Text)

Max Activating Token Index: 899

Text #19

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8095. Min Act: -0.1700

Data Index: 7089207 (Open Web Text)

Max Activating Token Index: 1004