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

Dataset: Open Web Text

Neuron 186 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: 4.0138. Min Range: -4.0138

Max Act: 4.0138. Min Act: -0.1700

Data Index: 3914979 (Open Web Text)

Max Activating Token Index: 355

Text #1

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9971. Min Act: -0.1700

Data Index: 4222520 (Open Web Text)

Max Activating Token Index: 682

Text #2

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9777. Min Act: -0.1700

Data Index: 3869477 (Open Web Text)

Max Activating Token Index: 267

Text #3

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9747. Min Act: -0.1700

Data Index: 2198527 (Open Web Text)

Max Activating Token Index: 456

Text #4

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9942. Min Act: -0.1700

Data Index: 1847228 (Open Web Text)

Max Activating Token Index: 408

Text #5

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9718. Min Act: -0.1700

Data Index: 6077937 (Open Web Text)

Max Activating Token Index: 402

Text #6

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9440. Min Act: -0.1700

Data Index: 4460869 (Open Web Text)

Max Activating Token Index: 137

Text #7

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9573. Min Act: -0.1700

Data Index: 6726204 (Open Web Text)

Max Activating Token Index: 532

Text #8

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9535. Min Act: -0.1700

Data Index: 3285899 (Open Web Text)

Max Activating Token Index: 189

Text #9

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9497. Min Act: -0.1700

Data Index: 6795244 (Open Web Text)

Max Activating Token Index: 97

Text #10

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.8974. Min Act: -0.1700

Data Index: 2217165 (Open Web Text)

Max Activating Token Index: 316

Text #11

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9201. Min Act: -0.1700

Data Index: 40765 (Open Web Text)

Max Activating Token Index: 284

Text #12

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9149. Min Act: -0.1700

Data Index: 235127 (Open Web Text)

Max Activating Token Index: 262

Text #13

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.9319. Min Act: -0.1700

Data Index: 4196174 (Open Web Text)

Max Activating Token Index: 240

Text #14

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.8912. Min Act: -0.1700

Data Index: 3250710 (Open Web Text)

Max Activating Token Index: 336

Text #15

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.8885. Min Act: -0.1700

Data Index: 2452370 (Open Web Text)

Max Activating Token Index: 396

Text #16

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.8964. Min Act: -0.1700

Data Index: 1168626 (Open Web Text)

Max Activating Token Index: 43

Text #17

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.8799. Min Act: -0.1700

Data Index: 5433738 (Open Web Text)

Max Activating Token Index: 172

Text #18

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.8781. Min Act: -0.1700

Data Index: 4163939 (Open Web Text)

Max Activating Token Index: 538

Text #19

Max Range: 4.0138. Min Range: -4.0138

Max Act: 3.8863. Min Act: -0.1700

Data Index: 2515214 (Open Web Text)

Max Activating Token Index: 945