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

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

Neuron 1181 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: 6.0141. Min Range: -6.0141

Max Act: 6.0141. Min Act: -0.0000

Data Index: 971594 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 6.0141. Min Range: -6.0141

Max Act: 5.7340. Min Act: -0.0000

Data Index: 355088 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.9300. Min Act: -0.0000

Data Index: 1174961 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 6.0141. Min Range: -6.0141

Max Act: 5.1010. Min Act: -0.0000

Data Index: 612494 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.7759. Min Act: -0.0000

Data Index: 643808 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.7583. Min Act: -0.0000

Data Index: 133965 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 6.0141. Min Range: -6.0141

Max Act: 5.0996. Min Act: -0.0000

Data Index: 858291 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 6.0141. Min Range: -6.0141

Max Act: 5.3870. Min Act: -0.0000

Data Index: 1284264 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.8654. Min Act: -0.0000

Data Index: 1066774 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.6521. Min Act: -0.0000

Data Index: 499992 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.7777. Min Act: -0.0000

Data Index: 1184487 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.6729. Min Act: -0.0000

Data Index: 697909 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.8491. Min Act: -0.0000

Data Index: 410122 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.5810. Min Act: -0.0000

Data Index: 109081 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 6.0141. Min Range: -6.0141

Max Act: 5.2578. Min Act: -0.0000

Data Index: 219966 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.2046. Min Act: -0.0000

Data Index: 487090 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.1894. Min Act: -0.0000

Data Index: 370347 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.3855. Min Act: -0.0000

Data Index: 726708 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.2010. Min Act: -0.0000

Data Index: 429310 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 6.0141. Min Range: -6.0141

Max Act: 4.2192. Min Act: -0.0000

Data Index: 1322039 (C4 (Web Text))

Max Activating Token Index: 456