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

Dataset: Open Web Text

Neuron 1939 in Layer 5

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: 3.4489. Min Range: -3.4489

Max Act: 3.4457. Min Act: -0.1700

Data Index: 280703 (Open Web Text)

Max Activating Token Index: 311

Text #1

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.4489. Min Act: -0.1700

Data Index: 2562610 (Open Web Text)

Max Activating Token Index: 420

Text #2

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.4218. Min Act: -0.1700

Data Index: 8544245 (Open Web Text)

Max Activating Token Index: 122

Text #3

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.4151. Min Act: -0.1700

Data Index: 2455672 (Open Web Text)

Max Activating Token Index: 298

Text #4

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.4198. Min Act: -0.1700

Data Index: 7895724 (Open Web Text)

Max Activating Token Index: 462

Text #5

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3936. Min Act: -0.1700

Data Index: 8050349 (Open Web Text)

Max Activating Token Index: 253

Text #6

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3980. Min Act: -0.1700

Data Index: 2146698 (Open Web Text)

Max Activating Token Index: 46

Text #7

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.4021. Min Act: -0.1700

Data Index: 6231474 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.4135. Min Act: -0.1700

Data Index: 4245507 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3709. Min Act: -0.1700

Data Index: 2958847 (Open Web Text)

Max Activating Token Index: 234

Text #10

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3984. Min Act: -0.1700

Data Index: 1688260 (Open Web Text)

Max Activating Token Index: 91

Text #11

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3877. Min Act: -0.1700

Data Index: 7646016 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3687. Min Act: -0.1700

Data Index: 2235645 (Open Web Text)

Max Activating Token Index: 132

Text #13

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3713. Min Act: -0.1700

Data Index: 4928496 (Open Web Text)

Max Activating Token Index: 526

Text #14

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3396. Min Act: -0.1700

Data Index: 1123456 (Open Web Text)

Max Activating Token Index: 480

Text #15

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3508. Min Act: -0.1700

Data Index: 8196321 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3476. Min Act: -0.1700

Data Index: 5675593 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3412. Min Act: -0.1700

Data Index: 3134618 (Open Web Text)

Max Activating Token Index: 223

Text #18

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3396. Min Act: -0.1700

Data Index: 1902504 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 3.4489. Min Range: -3.4489

Max Act: 3.3213. Min Act: -0.1700

Data Index: 5771318 (Open Web Text)

Max Activating Token Index: 350