Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 445 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.4281. Min Act: -0.0001

Data Index: 255422 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.4413. Min Act: -0.0001

Data Index: 998346 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3968. Min Act: -0.0001

Data Index: 109585 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.4091. Min Act: -0.0001

Data Index: 94264 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3688. Min Act: -0.0001

Data Index: 751702 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3487. Min Act: -0.0001

Data Index: 956515 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3435. Min Act: -0.0001

Data Index: 845977 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3394. Min Act: -0.0001

Data Index: 902988 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3305. Min Act: -0.0001

Data Index: 31124 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3325. Min Act: -0.0001

Data Index: 633993 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3160. Min Act: -0.0001

Data Index: 814899 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3136. Min Act: -0.0001

Data Index: 1271435 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3117. Min Act: -0.0001

Data Index: 851769 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3103. Min Act: -0.0001

Data Index: 663675 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2919. Min Act: -0.0001

Data Index: 789644 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3011. Min Act: -0.0001

Data Index: 980295 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3193. Min Act: -0.0001

Data Index: 19437 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2978. Min Act: -0.0001

Data Index: 35201 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2979. Min Act: -0.0001

Data Index: 1058226 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2914. Min Act: -0.0001

Data Index: 782818 (C4 (Web Text))

Max Activating Token Index: 832