Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3716 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4376. Min Act: -0.0000

Data Index: 94710 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4209. Min Act: -0.0000

Data Index: 907189 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4245. Min Act: -0.0000

Data Index: 973799 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1335710 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3916. Min Act: -0.0000

Data Index: 539633 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4232. Min Act: -0.0000

Data Index: 829503 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4076. Min Act: -0.0000

Data Index: 706609 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3617. Min Act: -0.0000

Data Index: 899847 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1102185 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1105063 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1352284 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1304617 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3380. Min Act: -0.0000

Data Index: 920451 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3342. Min Act: -0.0000

Data Index: 565377 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3328. Min Act: -0.0000

Data Index: 166754 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1025628 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3280. Min Act: -0.0000

Data Index: 77750 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1255295 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1010499 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3033. Min Act: -0.0000

Data Index: 335338 (C4 (Web Text))

Max Activating Token Index: 277