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

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

Neuron 2629 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.7764. Min Act: -0.0001

Data Index: 141259 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.1763. Min Act: -0.0001

Data Index: 1339539 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.1700. Min Act: -0.0001

Data Index: 1020823 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.3010. Min Act: -0.0001

Data Index: 788917 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.3009. Min Act: -0.0001

Data Index: 1198036 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.1167. Min Act: -0.0001

Data Index: 264091 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.1965. Min Act: -0.0001

Data Index: 617544 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.1829. Min Act: -0.0001

Data Index: 429274 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.1547. Min Act: -0.0001

Data Index: 725294 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.1640. Min Act: -0.0001

Data Index: 602916 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.0063. Min Act: -0.0001

Data Index: 741141 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 3.7764. Min Range: -3.7764

Max Act: 2.9835. Min Act: -0.0001

Data Index: 944070 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 3.7764. Min Range: -3.7764

Max Act: 2.8126. Min Act: -0.0001

Data Index: 973714 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 3.7764. Min Range: -3.7764

Max Act: 2.9228. Min Act: -0.0001

Data Index: 1148292 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.0534. Min Act: -0.0001

Data Index: 777206 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 3.7764. Min Range: -3.7764

Max Act: 2.8942. Min Act: -0.0001

Data Index: 771964 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 3.7764. Min Range: -3.7764

Max Act: 2.8987. Min Act: -0.0001

Data Index: 1208946 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 3.7764. Min Range: -3.7764

Max Act: 2.8874. Min Act: -0.0001

Data Index: 425505 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 3.7764. Min Range: -3.7764

Max Act: 2.8752. Min Act: -0.0001

Data Index: 852013 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 3.7764. Min Range: -3.7764

Max Act: 3.0006. Min Act: -0.0001

Data Index: 47227 (C4 (Web Text))

Max Activating Token Index: 788