Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2605 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.8153. Min Act: -0.0001
Data Index: 198453 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.5701. Min Act: -0.0001
Data Index: 537226 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.5149. Min Act: -0.0001
Data Index: 1560493 (Python Code)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.5482. Min Act: -0.0001
Data Index: 1371407 (Python Code)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.5432. Min Act: -0.0001
Data Index: 79375 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4475. Min Act: -0.0001
Data Index: 1151353 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4558. Min Act: -0.0001
Data Index: 1628119 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.5178. Min Act: -0.0001
Data Index: 1407525 (Python Code)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4990. Min Act: -0.0000
Data Index: 1611930 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4370. Min Act: -0.0001
Data Index: 1500968 (Python Code)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4492. Min Act: -0.0001
Data Index: 1024750 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4507. Min Act: -0.0001
Data Index: 1543108 (Python Code)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4901. Min Act: -0.0001
Data Index: 1363767 (Python Code)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4237. Min Act: -0.0001
Data Index: 325169 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4570. Min Act: -0.0000
Data Index: 1523919 (Python Code)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4680. Min Act: -0.0001
Data Index: 1426360 (Python Code)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4839. Min Act: -0.0001
Data Index: 1553423 (Python Code)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4798. Min Act: -0.0000
Data Index: 320884 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.4232. Min Act: -0.0001
Data Index: 1472752 (Python Code)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.3973. Min Act: -0.0001
Data Index: 1464646 (Python Code)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19