Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4297 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.8220. Min Act: -0.0001
Data Index: 1382655 (Python Code)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.6216. Min Act: -0.0001
Data Index: 1563919 (Python Code)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.5721. Min Act: -0.0001
Data Index: 1602969 (Python Code)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.4930. Min Act: -0.0001
Data Index: 1440790 (Python Code)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.4845. Min Act: -0.0001
Data Index: 1467932 (Python Code)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.3927. Min Act: -0.0001
Data Index: 1622134 (Python Code)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.5330. Min Act: -0.0001
Data Index: 1531589 (Python Code)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.3265. Min Act: -0.0001
Data Index: 1364479 (Python Code)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.3523. Min Act: -0.0001
Data Index: 1396224 (Python Code)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.4333. Min Act: -0.0001
Data Index: 1608008 (Python Code)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.2670. Min Act: -0.0001
Data Index: 1577771 (Python Code)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.3339. Min Act: -0.0001
Data Index: 1363619 (Python Code)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.2306. Min Act: -0.0001
Data Index: 1372077 (Python Code)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.3962. Min Act: -0.0001
Data Index: 1548229 (Python Code)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.2640. Min Act: -0.0001
Data Index: 1473563 (Python Code)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.4241. Min Act: -0.0001
Data Index: 1652612 (Python Code)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.2430. Min Act: -0.0001
Data Index: 1492069 (Python Code)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.2365. Min Act: -0.0001
Data Index: 1394835 (Python Code)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.3061. Min Act: -0.0001
Data Index: 1493294 (Python Code)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.2881. Min Act: -0.0001
Data Index: 1451010 (Python Code)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19