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

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

Neuron 5897 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7981. Min Range: -4.7981

Max Act: 4.7981. Min Act: -0.0000

Data Index: 757602 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 4.7981. Min Range: -4.7981

Max Act: 4.1008. Min Act: -0.0000

Data Index: 856373 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 4.7981. Min Range: -4.7981

Max Act: 4.4927. Min Act: -0.0000

Data Index: 1172037 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 4.7981. Min Range: -4.7981

Max Act: 4.1169. Min Act: -0.0000

Data Index: 765624 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 4.7981. Min Range: -4.7981

Max Act: 4.4728. Min Act: -0.0000

Data Index: 1321530 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 4.7981. Min Range: -4.7981

Max Act: 3.9375. Min Act: -0.0000

Data Index: 422027 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 4.7981. Min Range: -4.7981

Max Act: 3.3979. Min Act: -0.0000

Data Index: 190175 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 4.7981. Min Range: -4.7981

Max Act: 3.0916. Min Act: -0.0000

Data Index: 315946 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 4.7981. Min Range: -4.7981

Max Act: 3.2377. Min Act: -0.0000

Data Index: 133420 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 4.7981. Min Range: -4.7981

Max Act: 2.7799. Min Act: -0.0000

Data Index: 793352 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 4.7981. Min Range: -4.7981

Max Act: 2.7623. Min Act: -0.0000

Data Index: 1006269 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 4.7981. Min Range: -4.7981

Max Act: 2.8575. Min Act: -0.0000

Data Index: 1329747 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 4.7981. Min Range: -4.7981

Max Act: 2.8278. Min Act: -0.0000

Data Index: 1343197 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 4.7981. Min Range: -4.7981

Max Act: 2.6527. Min Act: -0.0000

Data Index: 993817 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 4.7981. Min Range: -4.7981

Max Act: 2.9265. Min Act: -0.0000

Data Index: 1283620 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 4.7981. Min Range: -4.7981

Max Act: 2.6322. Min Act: -0.0000

Data Index: 622237 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 4.7981. Min Range: -4.7981

Max Act: 2.6281. Min Act: -0.0000

Data Index: 85451 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 4.7981. Min Range: -4.7981

Max Act: 2.6282. Min Act: -0.0000

Data Index: 191835 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 4.7981. Min Range: -4.7981

Max Act: 2.8950. Min Act: -0.0000

Data Index: 1113053 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 4.7981. Min Range: -4.7981

Max Act: 2.5533. Min Act: -0.0000

Data Index: 440398 (C4 (Web Text))

Max Activating Token Index: 388