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

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

Neuron 1304 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.2622. Min Act: -0.0001

Data Index: 1152844 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.2916. Min Act: -0.0001

Data Index: 676527 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1717. Min Act: -0.0001

Data Index: 806176 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.2252. Min Act: -0.0001

Data Index: 217555 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.2103. Min Act: -0.0001

Data Index: 907518 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1673. Min Act: -0.0001

Data Index: 1185237 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1645. Min Act: -0.0001

Data Index: 866914 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.2676. Min Act: -0.0001

Data Index: 1103472 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0962. Min Act: -0.0001

Data Index: 466731 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1270. Min Act: -0.0001

Data Index: 263796 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0881. Min Act: -0.0001

Data Index: 783834 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0559. Min Act: -0.0001

Data Index: 274084 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1482. Min Act: -0.0001

Data Index: 451207 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0808. Min Act: -0.0001

Data Index: 247528 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1013. Min Act: -0.0001

Data Index: 398579 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0569. Min Act: -0.0001

Data Index: 764534 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0236. Min Act: -0.0001

Data Index: 1126353 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0767. Min Act: -0.0001

Data Index: 824382 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0231. Min Act: -0.0001

Data Index: 195525 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0825. Min Act: -0.0001

Data Index: 497793 (C4 (Web Text))

Max Activating Token Index: 1000