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

Dataset: Open Web Text

Neuron 2726 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: 3.4543. Min Range: -3.4543

Max Act: 3.4543. Min Act: -0.1700

Data Index: 3874788 (Open Web Text)

Max Activating Token Index: 653

Text #1

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.3755. Min Act: -0.1700

Data Index: 874167 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.3856. Min Act: -0.1700

Data Index: 5786282 (Open Web Text)

Max Activating Token Index: 183

Text #3

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.3593. Min Act: -0.1700

Data Index: 246587 (Open Web Text)

Max Activating Token Index: 573

Text #4

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.3648. Min Act: -0.1700

Data Index: 7251309 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.3010. Min Act: -0.1700

Data Index: 8214314 (Open Web Text)

Max Activating Token Index: 436

Text #6

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.3048. Min Act: -0.1700

Data Index: 7371901 (Open Web Text)

Max Activating Token Index: 982

Text #7

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.3054. Min Act: -0.1700

Data Index: 2134593 (Open Web Text)

Max Activating Token Index: 281

Text #8

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.3029. Min Act: -0.1700

Data Index: 1444310 (Open Web Text)

Max Activating Token Index: 653

Text #9

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.3169. Min Act: -0.1700

Data Index: 1741050 (Open Web Text)

Max Activating Token Index: 135

Text #10

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.2273. Min Act: -0.1700

Data Index: 2453630 (Open Web Text)

Max Activating Token Index: 690

Text #11

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.2091. Min Act: -0.1700

Data Index: 347763 (Open Web Text)

Max Activating Token Index: 544

Text #12

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.2269. Min Act: -0.1700

Data Index: 5877624 (Open Web Text)

Max Activating Token Index: 139

Text #13

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.2267. Min Act: -0.1700

Data Index: 4282111 (Open Web Text)

Max Activating Token Index: 269

Text #14

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.2116. Min Act: -0.1700

Data Index: 2266010 (Open Web Text)

Max Activating Token Index: 268

Text #15

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.1947. Min Act: -0.1700

Data Index: 8288832 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.2020. Min Act: -0.1700

Data Index: 6866448 (Open Web Text)

Max Activating Token Index: 732

Text #17

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.1794. Min Act: -0.1700

Data Index: 6411472 (Open Web Text)

Max Activating Token Index: 905

Text #18

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.2015. Min Act: -0.1700

Data Index: 3262527 (Open Web Text)

Max Activating Token Index: 438

Text #19

Max Range: 3.4543. Min Range: -3.4543

Max Act: 3.1942. Min Act: -0.1700

Data Index: 573901 (Open Web Text)

Max Activating Token Index: 402