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

Dataset: Open Web Text

Neuron 2761 in Layer 2

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: 5.3164. Min Range: -5.3164

Max Act: 5.3164. Min Act: -0.1700

Data Index: 6385727 (Open Web Text)

Max Activating Token Index: 408

Text #1

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.3078. Min Act: -0.1700

Data Index: 3319568 (Open Web Text)

Max Activating Token Index: 323

Text #2

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.3018. Min Act: -0.1700

Data Index: 4905515 (Open Web Text)

Max Activating Token Index: 674

Text #3

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.2981. Min Act: -0.1700

Data Index: 8713606 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.3029. Min Act: -0.1700

Data Index: 4027152 (Open Web Text)

Max Activating Token Index: 679

Text #5

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.2530. Min Act: -0.1700

Data Index: 6069893 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.2487. Min Act: -0.1700

Data Index: 6651428 (Open Web Text)

Max Activating Token Index: 385

Text #7

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.2647. Min Act: -0.1700

Data Index: 5481876 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.2521. Min Act: -0.1700

Data Index: 3041930 (Open Web Text)

Max Activating Token Index: 108

Text #9

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.2206. Min Act: -0.1700

Data Index: 2247166 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.2320. Min Act: -0.1700

Data Index: 7155675 (Open Web Text)

Max Activating Token Index: 762

Text #11

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.2103. Min Act: -0.1700

Data Index: 5616250 (Open Web Text)

Max Activating Token Index: 990

Text #12

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.2349. Min Act: -0.1700

Data Index: 984704 (Open Web Text)

Max Activating Token Index: 53

Text #13

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.2279. Min Act: -0.1700

Data Index: 5385534 (Open Web Text)

Max Activating Token Index: 873

Text #14

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.1945. Min Act: -0.1700

Data Index: 5568102 (Open Web Text)

Max Activating Token Index: 455

Text #15

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.1955. Min Act: -0.1700

Data Index: 5815456 (Open Web Text)

Max Activating Token Index: 411

Text #16

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.2080. Min Act: -0.1700

Data Index: 5663493 (Open Web Text)

Max Activating Token Index: 306

Text #17

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.1962. Min Act: -0.1700

Data Index: 3769671 (Open Web Text)

Max Activating Token Index: 374

Text #18

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.1995. Min Act: -0.1700

Data Index: 3030372 (Open Web Text)

Max Activating Token Index: 506

Text #19

Max Range: 5.3164. Min Range: -5.3164

Max Act: 5.1841. Min Act: -0.1700

Data Index: 2736452 (Open Web Text)

Max Activating Token Index: 533