Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2637 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2947. Min Range: -2.2947
Max Act: 2.2947. Min Act: -0.0001
Data Index: 1282980 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2947. Min Range: -2.2947
Max Act: 2.1330. Min Act: -0.0001
Data Index: 957366 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2947. Min Range: -2.2947
Max Act: 2.0394. Min Act: -0.0001
Data Index: 787029 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.9995. Min Act: -0.0001
Data Index: 918397 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.8573. Min Act: -0.0001
Data Index: 220879 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2947. Min Range: -2.2947
Max Act: 2.0317. Min Act: -0.0001
Data Index: 67324 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.7668. Min Act: -0.0001
Data Index: 786619 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.7966. Min Act: -0.0001
Data Index: 472828 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.7632. Min Act: -0.0001
Data Index: 415596 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.6081. Min Act: -0.0001
Data Index: 1271727 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.8880. Min Act: -0.0001
Data Index: 794659 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.8538. Min Act: -0.0001
Data Index: 1341069 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.6990. Min Act: -0.0001
Data Index: 140744 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.7105. Min Act: -0.0001
Data Index: 949060 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.5677. Min Act: -0.0001
Data Index: 930400 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.8551. Min Act: -0.0001
Data Index: 354454 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.8608. Min Act: -0.0001
Data Index: 1263659 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.6598. Min Act: -0.0001
Data Index: 128784 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.7145. Min Act: -0.0001
Data Index: 895079 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2947. Min Range: -2.2947
Max Act: 1.6748. Min Act: -0.0001
Data Index: 1069687 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19