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

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

Neuron 3500 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5364. Min Range: -2.5364

Max Act: 2.5364. Min Act: -0.0000

Data Index: 1018079 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 2.5364. Min Range: -2.5364

Max Act: 2.4942. Min Act: -0.0000

Data Index: 131278 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 2.5364. Min Range: -2.5364

Max Act: 2.2666. Min Act: -0.0000

Data Index: 1170987 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 2.5364. Min Range: -2.5364

Max Act: 2.2671. Min Act: -0.0000

Data Index: 176281 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 2.5364. Min Range: -2.5364

Max Act: 2.2527. Min Act: -0.0000

Data Index: 1162856 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 2.5364. Min Range: -2.5364

Max Act: 2.1286. Min Act: -0.0000

Data Index: 762661 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 2.5364. Min Range: -2.5364

Max Act: 2.2134. Min Act: -0.0000

Data Index: 1218216 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 2.5364. Min Range: -2.5364

Max Act: 2.0109. Min Act: -0.0000

Data Index: 882104 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 2.5364. Min Range: -2.5364

Max Act: 1.9894. Min Act: -0.0000

Data Index: 1282558 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 2.5364. Min Range: -2.5364

Max Act: 2.0943. Min Act: -0.0000

Data Index: 1055441 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 2.5364. Min Range: -2.5364

Max Act: 2.0967. Min Act: -0.0000

Data Index: 1014646 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 2.5364. Min Range: -2.5364

Max Act: 1.8599. Min Act: -0.0000

Data Index: 1303394 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 2.5364. Min Range: -2.5364

Max Act: 1.8355. Min Act: -0.0000

Data Index: 252163 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 2.5364. Min Range: -2.5364

Max Act: 1.8980. Min Act: -0.0000

Data Index: 844179 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 2.5364. Min Range: -2.5364

Max Act: 1.8945. Min Act: -0.0000

Data Index: 1142595 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 2.5364. Min Range: -2.5364

Max Act: 1.8953. Min Act: -0.0000

Data Index: 472200 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 2.5364. Min Range: -2.5364

Max Act: 1.8881. Min Act: -0.0000

Data Index: 1108397 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 2.5364. Min Range: -2.5364

Max Act: 1.8868. Min Act: -0.0000

Data Index: 842275 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 2.5364. Min Range: -2.5364

Max Act: 1.8509. Min Act: -0.0000

Data Index: 897775 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 2.5364. Min Range: -2.5364

Max Act: 1.8530. Min Act: -0.0000

Data Index: 941514 (C4 (Web Text))

Max Activating Token Index: 146