Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1975 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.5389. Min Act: -0.0001
Data Index: 1448554 (Python Code)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.5337. Min Act: -0.0001
Data Index: 1602960 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4875. Min Act: -0.0001
Data Index: 1617558 (Python Code)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4817. Min Act: -0.0001
Data Index: 1389007 (Python Code)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4307. Min Act: -0.0001
Data Index: 1564346 (Python Code)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4341. Min Act: -0.0001
Data Index: 1414296 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4183. Min Act: -0.0001
Data Index: 380861 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4636. Min Act: -0.0001
Data Index: 1462740 (Python Code)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4424. Min Act: -0.0001
Data Index: 1582854 (Python Code)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4171. Min Act: -0.0001
Data Index: 856045 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.3822. Min Act: -0.0001
Data Index: 1625301 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4387. Min Act: -0.0001
Data Index: 1657067 (Python Code)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.3847. Min Act: -0.0001
Data Index: 855107 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4042. Min Act: -0.0001
Data Index: 1636776 (Python Code)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4194. Min Act: -0.0001
Data Index: 905514 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4301. Min Act: -0.0001
Data Index: 832431 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.3931. Min Act: -0.0001
Data Index: 507872 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.4218. Min Act: -0.0001
Data Index: 386397 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.3887. Min Act: -0.0001
Data Index: 1488050 (Python Code)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5389. Min Range: -0.5389
Max Act: 0.3877. Min Act: -0.0001
Data Index: 1537315 (Python Code)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19