Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2860 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.7329. Min Act: -0.0001
Data Index: 1080526 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.5385. Min Act: -0.0001
Data Index: 711654 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.0028. Min Act: -0.0001
Data Index: 128026 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.3701. Min Act: -0.0001
Data Index: 301213 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.4307. Min Act: -0.0001
Data Index: 927330 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.5539. Min Act: -0.0001
Data Index: 1222442 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.2154. Min Act: -0.0001
Data Index: 838599 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7329. Min Range: -2.7329
Max Act: 1.8325. Min Act: -0.0001
Data Index: 1053832 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.2490. Min Act: -0.0001
Data Index: 977484 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.1874. Min Act: -0.0001
Data Index: 1065956 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7329. Min Range: -2.7329
Max Act: 1.9300. Min Act: -0.0001
Data Index: 242204 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7329. Min Range: -2.7329
Max Act: 1.9117. Min Act: -0.0001
Data Index: 1106760 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7329. Min Range: -2.7329
Max Act: 1.4525. Min Act: -0.0001
Data Index: 898664 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7329. Min Range: -2.7329
Max Act: 1.3638. Min Act: -0.0001
Data Index: 1233843 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7329. Min Range: -2.7329
Max Act: 1.6985. Min Act: -0.0001
Data Index: 1215511 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7329. Min Range: -2.7329
Max Act: 1.8886. Min Act: -0.0001
Data Index: 1113804 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7329. Min Range: -2.7329
Max Act: 2.1373. Min Act: -0.0001
Data Index: 1112623 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7329. Min Range: -2.7329
Max Act: 1.6892. Min Act: -0.0001
Data Index: 555820 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7329. Min Range: -2.7329
Max Act: 1.5852. Min Act: -0.0001
Data Index: 217983 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7329. Min Range: -2.7329
Max Act: 1.8590. Min Act: -0.0001
Data Index: 63068 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19