Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 248 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.5294. Min Range: -1.5294
Max Act: 1.5294. Min Act: -0.0001
Data Index: 1045747 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5294. Min Range: -1.5294
Max Act: 1.1654. Min Act: -0.0001
Data Index: 1247796 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5294. Min Range: -1.5294
Max Act: 1.1438. Min Act: -0.0001
Data Index: 1030660 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5294. Min Range: -1.5294
Max Act: 1.0687. Min Act: -0.0001
Data Index: 420952 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5294. Min Range: -1.5294
Max Act: 1.0518. Min Act: -0.0001
Data Index: 1145990 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5294. Min Range: -1.5294
Max Act: 0.9439. Min Act: -0.0001
Data Index: 1273236 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5294. Min Range: -1.5294
Max Act: 1.0708. Min Act: -0.0001
Data Index: 509662 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5294. Min Range: -1.5294
Max Act: 1.0609. Min Act: -0.0001
Data Index: 1025040 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5294. Min Range: -1.5294
Max Act: 1.0896. Min Act: -0.0001
Data Index: 686734 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5294. Min Range: -1.5294
Max Act: 0.9875. Min Act: -0.0001
Data Index: 1000580 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5294. Min Range: -1.5294
Max Act: 1.0748. Min Act: -0.0001
Data Index: 454927 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5294. Min Range: -1.5294
Max Act: 0.9926. Min Act: -0.0001
Data Index: 431372 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5294. Min Range: -1.5294
Max Act: 1.0048. Min Act: -0.0001
Data Index: 355288 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5294. Min Range: -1.5294
Max Act: 0.9494. Min Act: -0.0001
Data Index: 693275 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5294. Min Range: -1.5294
Max Act: 0.9105. Min Act: -0.0001
Data Index: 1186731 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5294. Min Range: -1.5294
Max Act: 0.9258. Min Act: -0.0001
Data Index: 898651 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5294. Min Range: -1.5294
Max Act: 0.9213. Min Act: -0.0001
Data Index: 431737 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5294. Min Range: -1.5294
Max Act: 0.9348. Min Act: -0.0001
Data Index: 312291 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5294. Min Range: -1.5294
Max Act: 0.9160. Min Act: -0.0001
Data Index: 440860 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5294. Min Range: -1.5294
Max Act: 0.8764. Min Act: -0.0001
Data Index: 465855 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19