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

Dataset: Open Web Text

Neuron 1616 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: 3.4521. Min Range: -3.4521

Max Act: 3.4521. Min Act: -0.1700

Data Index: 4019185 (Open Web Text)

Max Activating Token Index: 114

Text #1

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.4000. Min Act: -0.1700

Data Index: 804300 (Open Web Text)

Max Activating Token Index: 152

Text #2

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3710. Min Act: -0.1700

Data Index: 6877278 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3732. Min Act: -0.1700

Data Index: 8288826 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3603. Min Act: -0.1700

Data Index: 3805613 (Open Web Text)

Max Activating Token Index: 164

Text #5

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3251. Min Act: -0.1700

Data Index: 8477791 (Open Web Text)

Max Activating Token Index: 204

Text #6

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3375. Min Act: -0.1700

Data Index: 694817 (Open Web Text)

Max Activating Token Index: 184

Text #7

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3362. Min Act: -0.1700

Data Index: 3225964 (Open Web Text)

Max Activating Token Index: 687

Text #8

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3239. Min Act: -0.1700

Data Index: 694820 (Open Web Text)

Max Activating Token Index: 129

Text #9

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3330. Min Act: -0.1700

Data Index: 4019157 (Open Web Text)

Max Activating Token Index: 606

Text #10

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3236. Min Act: -0.1700

Data Index: 3805586 (Open Web Text)

Max Activating Token Index: 122

Text #11

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3199. Min Act: -0.1700

Data Index: 5994276 (Open Web Text)

Max Activating Token Index: 90

Text #12

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3200. Min Act: -0.1700

Data Index: 3805610 (Open Web Text)

Max Activating Token Index: 193

Text #13

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3053. Min Act: -0.1700

Data Index: 3805594 (Open Web Text)

Max Activating Token Index: 125

Text #14

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3083. Min Act: -0.1700

Data Index: 5307119 (Open Web Text)

Max Activating Token Index: 118

Text #15

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3011. Min Act: -0.1700

Data Index: 694807 (Open Web Text)

Max Activating Token Index: 108

Text #16

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.3125. Min Act: -0.1700

Data Index: 8477817 (Open Web Text)

Max Activating Token Index: 685

Text #17

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.2968. Min Act: -0.1700

Data Index: 7024967 (Open Web Text)

Max Activating Token Index: 33

Text #18

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.2832. Min Act: -0.1700

Data Index: 4251169 (Open Web Text)

Max Activating Token Index: 207

Text #19

Max Range: 3.4521. Min Range: -3.4521

Max Act: 3.2910. Min Act: -0.1700

Data Index: 5876950 (Open Web Text)

Max Activating Token Index: 17