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

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

Neuron 3420 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: 3.3224. Min Range: -3.3224

Max Act: 3.3224. Min Act: -0.0000

Data Index: 1127360 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.8622. Min Act: -0.0000

Data Index: 702341 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.9459. Min Act: -0.0000

Data Index: 1356816 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.7269. Min Act: -0.0000

Data Index: 97313 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.4756. Min Act: -0.0000

Data Index: 971767 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.5651. Min Act: -0.0000

Data Index: 472708 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.7657. Min Act: -0.0000

Data Index: 660742 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.6713. Min Act: -0.0000

Data Index: 888584 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.5789. Min Act: -0.0000

Data Index: 1017262 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.8170. Min Act: -0.0000

Data Index: 219642 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.5461. Min Act: -0.0000

Data Index: 93990 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.5189. Min Act: -0.0000

Data Index: 828074 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.4803. Min Act: -0.0000

Data Index: 183685 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.4437. Min Act: -0.0000

Data Index: 805231 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.4419. Min Act: -0.0000

Data Index: 1038178 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.4253. Min Act: -0.0000

Data Index: 318093 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.3058. Min Act: -0.0000

Data Index: 206524 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.4099. Min Act: -0.0000

Data Index: 1548483 (Python Code)

Max Activating Token Index: 87

Text #18

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.2838. Min Act: -0.0000

Data Index: 150028 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 3.3224. Min Range: -3.3224

Max Act: 2.4112. Min Act: -0.0000

Data Index: 743632 (C4 (Web Text))

Max Activating Token Index: 546