Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4033 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.3483. Min Act: -0.0001
Data Index: 1482618 (Python Code)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.3122. Min Act: -0.0000
Data Index: 358184 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2652. Min Act: -0.0001
Data Index: 460614 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2856. Min Act: -0.0001
Data Index: 1307042 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2568. Min Act: -0.0000
Data Index: 827207 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2405. Min Act: -0.0001
Data Index: 1412269 (Python Code)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2403. Min Act: -0.0001
Data Index: 260626 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2371. Min Act: -0.0000
Data Index: 944942 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2413. Min Act: -0.0001
Data Index: 1380177 (Python Code)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2100. Min Act: -0.0000
Data Index: 806110 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2090. Min Act: -0.0000
Data Index: 645650 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2105. Min Act: -0.0001
Data Index: 87872 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2058. Min Act: -0.0001
Data Index: 1528864 (Python Code)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2023. Min Act: -0.0001
Data Index: 96909 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.1993. Min Act: -0.0001
Data Index: 69317 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.1994. Min Act: -0.0000
Data Index: 255306 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2002. Min Act: -0.0001
Data Index: 1394883 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2359. Min Act: -0.0001
Data Index: 1080068 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2032. Min Act: -0.0001
Data Index: 1041538 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3483. Min Range: -0.3483
Max Act: 0.2049. Min Act: -0.0000
Data Index: 226775 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19