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

Dataset: Open Web Text

Neuron 1796 in Layer 6

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: 5.4247. Min Range: -5.4247

Max Act: 5.4247. Min Act: -0.1700

Data Index: 3017023 (Open Web Text)

Max Activating Token Index: 555

Text #1

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.4106. Min Act: -0.1700

Data Index: 3678300 (Open Web Text)

Max Activating Token Index: 607

Text #2

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3463. Min Act: -0.1700

Data Index: 7951200 (Open Web Text)

Max Activating Token Index: 849

Text #3

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3961. Min Act: -0.1700

Data Index: 5495870 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3134. Min Act: -0.1700

Data Index: 4391843 (Open Web Text)

Max Activating Token Index: 781

Text #5

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3497. Min Act: -0.1700

Data Index: 1066830 (Open Web Text)

Max Activating Token Index: 1015

Text #6

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3025. Min Act: -0.1700

Data Index: 5260175 (Open Web Text)

Max Activating Token Index: 938

Text #7

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3500. Min Act: -0.1700

Data Index: 2829908 (Open Web Text)

Max Activating Token Index: 159

Text #8

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3426. Min Act: -0.1700

Data Index: 5912092 (Open Web Text)

Max Activating Token Index: 697

Text #9

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.2882. Min Act: -0.1700

Data Index: 821742 (Open Web Text)

Max Activating Token Index: 624

Text #10

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3177. Min Act: -0.1700

Data Index: 7327763 (Open Web Text)

Max Activating Token Index: 999

Text #11

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3168. Min Act: -0.1700

Data Index: 2208494 (Open Web Text)

Max Activating Token Index: 251

Text #12

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.2961. Min Act: -0.1700

Data Index: 6623601 (Open Web Text)

Max Activating Token Index: 885

Text #13

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3316. Min Act: -0.1700

Data Index: 4729972 (Open Web Text)

Max Activating Token Index: 489

Text #14

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.2854. Min Act: -0.1700

Data Index: 1925215 (Open Web Text)

Max Activating Token Index: 745

Text #15

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3152. Min Act: -0.1700

Data Index: 3659367 (Open Web Text)

Max Activating Token Index: 189

Text #16

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.3089. Min Act: -0.1700

Data Index: 7327777 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.2859. Min Act: -0.1700

Data Index: 5630372 (Open Web Text)

Max Activating Token Index: 329

Text #18

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.2622. Min Act: -0.1700

Data Index: 4798207 (Open Web Text)

Max Activating Token Index: 426

Text #19

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.2336. Min Act: -0.1700

Data Index: 3550544 (Open Web Text)

Max Activating Token Index: 515