Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 109 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.6376. Min Act: -0.0001

Data Index: 1330495 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5637. Min Act: -0.0001

Data Index: 85098 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5155. Min Act: -0.0001

Data Index: 892093 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.4950. Min Act: -0.0001

Data Index: 739105 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5183. Min Act: -0.0002

Data Index: 554364 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5168. Min Act: -0.0001

Data Index: 264583 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.4602. Min Act: -0.0001

Data Index: 1097084 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.4425. Min Act: -0.0001

Data Index: 362293 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.4595. Min Act: -0.0001

Data Index: 424775 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.4264. Min Act: -0.0001

Data Index: 1403239 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.4323. Min Act: -0.0001

Data Index: 928834 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.4224. Min Act: -0.0002

Data Index: 837562 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.4101. Min Act: -0.0002

Data Index: 228035 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.3988. Min Act: -0.0001

Data Index: 591394 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.3902. Min Act: -0.0001

Data Index: 620110 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.3872. Min Act: -0.0001

Data Index: 1178663 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.3963. Min Act: -0.0001

Data Index: 425724 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.4223. Min Act: -0.0001

Data Index: 1407117 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.3590. Min Act: -0.0001

Data Index: 1639264 (Python Code)

Max Activating Token Index: 583

Text #19

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.3906. Min Act: -0.0001

Data Index: 1380282 (Python Code)

Max Activating Token Index: 59