Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4385 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.5470. Min Range: -2.5470
Max Act: 2.5470. Min Act: -0.0001
Data Index: 264028 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5470. Min Range: -2.5470
Max Act: 2.4013. Min Act: -0.0001
Data Index: 1195053 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5470. Min Range: -2.5470
Max Act: 2.2161. Min Act: -0.0001
Data Index: 1067165 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5470. Min Range: -2.5470
Max Act: 2.0762. Min Act: -0.0000
Data Index: 1285900 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5470. Min Range: -2.5470
Max Act: 2.0354. Min Act: -0.0000
Data Index: 423821 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5470. Min Range: -2.5470
Max Act: 2.1441. Min Act: -0.0000
Data Index: 325930 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5470. Min Range: -2.5470
Max Act: 2.0550. Min Act: -0.0001
Data Index: 70417 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.8885. Min Act: -0.0001
Data Index: 1506263 (Python Code)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.8631. Min Act: -0.0000
Data Index: 1121008 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.8425. Min Act: -0.0001
Data Index: 909448 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.9544. Min Act: -0.0001
Data Index: 864492 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.8806. Min Act: -0.0001
Data Index: 1252399 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.9792. Min Act: -0.0000
Data Index: 1066850 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.8631. Min Act: -0.0000
Data Index: 292752 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.8421. Min Act: -0.0000
Data Index: 961253 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.8336. Min Act: -0.0001
Data Index: 991505 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.8435. Min Act: -0.0001
Data Index: 105258 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.7492. Min Act: -0.0001
Data Index: 5902 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.8293. Min Act: -0.0001
Data Index: 396587 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5470. Min Range: -2.5470
Max Act: 1.6237. Min Act: -0.0000
Data Index: 201455 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19