Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4190 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2237. Min Range: -2.2237
Max Act: 2.2237. Min Act: -0.0001
Data Index: 1541198 (Python Code)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.9234. Min Act: -0.0001
Data Index: 1386747 (Python Code)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.4397. Min Act: -0.0001
Data Index: 1460096 (Python Code)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.6431. Min Act: -0.0001
Data Index: 1457200 (Python Code)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.6914. Min Act: -0.0001
Data Index: 1425128 (Python Code)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.6145. Min Act: -0.0001
Data Index: 1608340 (Python Code)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.6802. Min Act: -0.0001
Data Index: 1387314 (Python Code)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.2286. Min Act: -0.0001
Data Index: 1633071 (Python Code)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.5615. Min Act: -0.0001
Data Index: 147637 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.5981. Min Act: -0.0000
Data Index: 1599071 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.5123. Min Act: -0.0001
Data Index: 22975 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.4994. Min Act: -0.0001
Data Index: 1403867 (Python Code)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.5305. Min Act: -0.0001
Data Index: 1509709 (Python Code)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.5597. Min Act: -0.0001
Data Index: 1648620 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.3338. Min Act: -0.0001
Data Index: 1376674 (Python Code)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.2856. Min Act: -0.0001
Data Index: 1373121 (Python Code)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.4566. Min Act: -0.0001
Data Index: 1619077 (Python Code)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.2317. Min Act: -0.0001
Data Index: 1489748 (Python Code)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.4998. Min Act: -0.0001
Data Index: 1113962 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2237. Min Range: -2.2237
Max Act: 1.4581. Min Act: -0.0001
Data Index: 1638005 (Python Code)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19