Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2952 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.9760. Min Act: -0.0001
Data Index: 693449 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0081. Min Range: -2.0081
Max Act: 2.0081. Min Act: -0.0001
Data Index: 304813 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.7036. Min Act: -0.0001
Data Index: 531168 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.3665. Min Act: -0.0001
Data Index: 641293 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.3531. Min Act: -0.0001
Data Index: 1408228 (Python Code)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.4019. Min Act: -0.0001
Data Index: 877548 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.2593. Min Act: -0.0001
Data Index: 432657 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.3781. Min Act: -0.0001
Data Index: 329314 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.2972. Min Act: -0.0001
Data Index: 854899 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.3674. Min Act: -0.0001
Data Index: 708485 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.3228. Min Act: -0.0001
Data Index: 341040 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.3193. Min Act: -0.0001
Data Index: 528466 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.2781. Min Act: -0.0001
Data Index: 1162814 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.2741. Min Act: -0.0001
Data Index: 1236991 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.3358. Min Act: -0.0001
Data Index: 770361 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.2634. Min Act: -0.0001
Data Index: 649068 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.1925. Min Act: -0.0001
Data Index: 814824 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.4253. Min Act: -0.0001
Data Index: 1039577 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.2564. Min Act: -0.0001
Data Index: 38566 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0081. Min Range: -2.0081
Max Act: 1.2124. Min Act: -0.0001
Data Index: 1072035 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19