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

Dataset: Open Web Text

Neuron 1299 in Layer 4

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: 3.4191. Min Range: -3.4191

Max Act: 3.4191. Min Act: -0.1700

Data Index: 145251 (Open Web Text)

Max Activating Token Index: 416

Text #1

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3438. Min Act: -0.1700

Data Index: 1417354 (Open Web Text)

Max Activating Token Index: 129

Text #2

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3466. Min Act: -0.1700

Data Index: 8159568 (Open Web Text)

Max Activating Token Index: 613

Text #3

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3391. Min Act: -0.1700

Data Index: 5193616 (Open Web Text)

Max Activating Token Index: 575

Text #4

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3079. Min Act: -0.1700

Data Index: 4621299 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2994. Min Act: -0.1700

Data Index: 6574115 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3267. Min Act: -0.1700

Data Index: 6168189 (Open Web Text)

Max Activating Token Index: 44

Text #7

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2956. Min Act: -0.1700

Data Index: 1406726 (Open Web Text)

Max Activating Token Index: 81

Text #8

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2739. Min Act: -0.1700

Data Index: 6531789 (Open Web Text)

Max Activating Token Index: 380

Text #9

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2646. Min Act: -0.1700

Data Index: 3514664 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2681. Min Act: -0.1700

Data Index: 1417360 (Open Web Text)

Max Activating Token Index: 112

Text #11

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2939. Min Act: -0.1700

Data Index: 6700605 (Open Web Text)

Max Activating Token Index: 737

Text #12

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2638. Min Act: -0.1700

Data Index: 5338891 (Open Web Text)

Max Activating Token Index: 322

Text #13

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2329. Min Act: -0.1700

Data Index: 8542225 (Open Web Text)

Max Activating Token Index: 207

Text #14

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2663. Min Act: -0.1700

Data Index: 4062401 (Open Web Text)

Max Activating Token Index: 497

Text #15

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2444. Min Act: -0.1700

Data Index: 2890651 (Open Web Text)

Max Activating Token Index: 252

Text #16

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2265. Min Act: -0.1700

Data Index: 1431259 (Open Web Text)

Max Activating Token Index: 283

Text #17

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2364. Min Act: -0.1700

Data Index: 968131 (Open Web Text)

Max Activating Token Index: 521

Text #18

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2057. Min Act: -0.1700

Data Index: 6558331 (Open Web Text)

Max Activating Token Index: 295

Text #19

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2157. Min Act: -0.1700

Data Index: 8811302 (Open Web Text)

Max Activating Token Index: 651