Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2392 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.4475. Min Act: -0.0001
Data Index: 718414 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.3270. Min Act: -0.0001
Data Index: 106725 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.3601. Min Act: -0.0001
Data Index: 1607666 (Python Code)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.2455. Min Act: -0.0001
Data Index: 1189006 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.2098. Min Act: -0.0001
Data Index: 610017 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.2091. Min Act: -0.0001
Data Index: 585249 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.1565. Min Act: -0.0001
Data Index: 1276035 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.1592. Min Act: -0.0001
Data Index: 1324778 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.0723. Min Act: -0.0001
Data Index: 873320 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.2067. Min Act: -0.0001
Data Index: 968775 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.0792. Min Act: -0.0001
Data Index: 826083 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.1082. Min Act: -0.0001
Data Index: 1166455 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.0660. Min Act: -0.0001
Data Index: 455638 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.0483. Min Act: -0.0001
Data Index: 1547359 (Python Code)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.0034. Min Act: -0.0001
Data Index: 762899 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.0288. Min Act: -0.0001
Data Index: 730712 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.0580. Min Act: -0.0001
Data Index: 915127 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4475. Min Range: -1.4475
Max Act: 0.9506. Min Act: -0.0001
Data Index: 571562 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4475. Min Range: -1.4475
Max Act: 1.0823. Min Act: -0.0001
Data Index: 30173 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4475. Min Range: -1.4475
Max Act: 0.9575. Min Act: -0.0001
Data Index: 860037 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19