Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2825 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.5055. Min Act: -0.0001
Data Index: 901778 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.5227. Min Act: -0.0001
Data Index: 37081 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4800. Min Act: -0.0001
Data Index: 514985 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4720. Min Act: -0.0001
Data Index: 1248336 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4716. Min Act: -0.0001
Data Index: 606349 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4510. Min Act: -0.0001
Data Index: 214850 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4964. Min Act: -0.0001
Data Index: 554529 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4635. Min Act: -0.0001
Data Index: 295930 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4777. Min Act: -0.0001
Data Index: 1310655 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4558. Min Act: -0.0001
Data Index: 1230879 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4545. Min Act: -0.0001
Data Index: 276740 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4574. Min Act: -0.0001
Data Index: 814493 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4571. Min Act: -0.0001
Data Index: 1186722 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4683. Min Act: -0.0001
Data Index: 366372 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4505. Min Act: -0.0001
Data Index: 945067 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4451. Min Act: -0.0001
Data Index: 53380 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4494. Min Act: -0.0001
Data Index: 484393 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4488. Min Act: -0.0001
Data Index: 1269099 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4460. Min Act: -0.0001
Data Index: 524377 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5227. Min Range: -0.5227
Max Act: 0.4456. Min Act: -0.0001
Data Index: 359315 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19