Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3133 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.2405. Min Range: -4.2405
Max Act: 4.2405. Min Act: -0.0001
Data Index: 380614 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2405. Min Range: -4.2405
Max Act: 3.2914. Min Act: -0.0001
Data Index: 127051 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2405. Min Range: -4.2405
Max Act: 3.8056. Min Act: -0.0001
Data Index: 638558 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.9937. Min Act: -0.0001
Data Index: 1330119 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.8680. Min Act: -0.0001
Data Index: 763994 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.6109. Min Act: -0.0001
Data Index: 300029 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.9578. Min Act: -0.0001
Data Index: 257843 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2405. Min Range: -4.2405
Max Act: 3.1311. Min Act: -0.0001
Data Index: 331446 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.9082. Min Act: -0.0001
Data Index: 1333189 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.8425. Min Act: -0.0001
Data Index: 1087938 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.7046. Min Act: -0.0001
Data Index: 427781 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.7783. Min Act: -0.0001
Data Index: 898081 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.2417. Min Act: -0.0001
Data Index: 749024 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.3752. Min Act: -0.0001
Data Index: 418137 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.4751. Min Act: -0.0001
Data Index: 834399 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.9640. Min Act: -0.0001
Data Index: 844807 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.6197. Min Act: -0.0001
Data Index: 14992 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.5411. Min Act: -0.0001
Data Index: 532910 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.4878. Min Act: -0.0001
Data Index: 1037603 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2405. Min Range: -4.2405
Max Act: 2.4084. Min Act: -0.0001
Data Index: 1144151 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19