Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4196 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.5101. Min Act: -0.0001
Data Index: 1304519 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.5046. Min Act: -0.0001
Data Index: 225990 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.8739. Min Act: -0.0000
Data Index: 86811 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.5397. Min Act: -0.0001
Data Index: 1216077 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.0993. Min Act: -0.0001
Data Index: 1326471 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.1926. Min Act: -0.0001
Data Index: 861998 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.3723. Min Act: -0.0001
Data Index: 1195590 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.3509. Min Act: -0.0001
Data Index: 703946 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.3455. Min Act: -0.0001
Data Index: 264233 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.1176. Min Act: -0.0001
Data Index: 464965 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8739. Min Range: -4.8739
Max Act: 3.8973. Min Act: -0.0000
Data Index: 686987 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.4453. Min Act: -0.0001
Data Index: 39823 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.2168. Min Act: -0.0001
Data Index: 91988 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8739. Min Range: -4.8739
Max Act: 3.8828. Min Act: -0.0001
Data Index: 554691 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.0037. Min Act: -0.0001
Data Index: 1049316 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.4715. Min Act: -0.0001
Data Index: 559524 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.2491. Min Act: -0.0001
Data Index: 870238 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.0072. Min Act: -0.0001
Data Index: 1293188 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8739. Min Range: -4.8739
Max Act: 3.7466. Min Act: -0.0000
Data Index: 622129 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8739. Min Range: -4.8739
Max Act: 4.0502. Min Act: -0.0000
Data Index: 576369 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19