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

Dataset: Open Web Text

Neuron 2359 in Layer 0

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: 1.3544. Min Range: -1.3544

Max Act: 1.3544. Min Act: -0.1700

Data Index: 3419848 (Open Web Text)

Max Activating Token Index: 211

Text #1

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3364. Min Act: -0.1700

Data Index: 6848609 (Open Web Text)

Max Activating Token Index: 209

Text #2

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3255. Min Act: -0.1700

Data Index: 706761 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3176. Min Act: -0.1700

Data Index: 4925098 (Open Web Text)

Max Activating Token Index: 215

Text #4

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3138. Min Act: -0.1700

Data Index: 5086241 (Open Web Text)

Max Activating Token Index: 191

Text #5

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.2982. Min Act: -0.1700

Data Index: 1262455 (Open Web Text)

Max Activating Token Index: 192

Text #6

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.2956. Min Act: -0.1700

Data Index: 3840010 (Open Web Text)

Max Activating Token Index: 199

Text #7

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3068. Min Act: -0.1700

Data Index: 8156054 (Open Web Text)

Max Activating Token Index: 208

Text #8

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3062. Min Act: -0.1700

Data Index: 7360428 (Open Web Text)

Max Activating Token Index: 212

Text #9

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3023. Min Act: -0.1700

Data Index: 3488618 (Open Web Text)

Max Activating Token Index: 208

Text #10

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.2936. Min Act: -0.1700

Data Index: 6801998 (Open Web Text)

Max Activating Token Index: 218

Text #11

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.2934. Min Act: -0.1700

Data Index: 5795692 (Open Web Text)

Max Activating Token Index: 205

Text #12

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3104. Min Act: -0.1700

Data Index: 3221092 (Open Web Text)

Max Activating Token Index: 216

Text #13

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3071. Min Act: -0.1700

Data Index: 3961023 (Open Web Text)

Max Activating Token Index: 212

Text #14

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.2995. Min Act: -0.1700

Data Index: 5529486 (Open Web Text)

Max Activating Token Index: 214

Text #15

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.2930. Min Act: -0.1700

Data Index: 4198906 (Open Web Text)

Max Activating Token Index: 216

Text #16

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3106. Min Act: -0.1700

Data Index: 2495423 (Open Web Text)

Max Activating Token Index: 206

Text #17

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3063. Min Act: -0.1700

Data Index: 2488806 (Open Web Text)

Max Activating Token Index: 218

Text #18

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.2964. Min Act: -0.1700

Data Index: 350584 (Open Web Text)

Max Activating Token Index: 207

Text #19

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3007. Min Act: -0.1700

Data Index: 4100476 (Open Web Text)

Max Activating Token Index: 209