Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1894 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.7942. Min Act: -0.0001
Data Index: 1647482 (Python Code)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.6625. Min Act: -0.0001
Data Index: 1003210 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.6815. Min Act: -0.0001
Data Index: 479730 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.7296. Min Act: -0.0001
Data Index: 637512 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.7532. Min Act: -0.0001
Data Index: 1286288 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.7258. Min Act: -0.0001
Data Index: 1597615 (Python Code)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.7063. Min Act: -0.0001
Data Index: 1314637 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.5866. Min Act: -0.0001
Data Index: 1470421 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.5786. Min Act: -0.0001
Data Index: 44072 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.5695. Min Act: -0.0001
Data Index: 719767 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.6478. Min Act: -0.0001
Data Index: 879753 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.5485. Min Act: -0.0001
Data Index: 508697 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.4985. Min Act: -0.0001
Data Index: 2629 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.5527. Min Act: -0.0001
Data Index: 159939 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.3924. Min Act: -0.0001
Data Index: 1337568 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.4093. Min Act: -0.0001
Data Index: 398702 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.5744. Min Act: -0.0001
Data Index: 689756 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.5838. Min Act: -0.0001
Data Index: 1313953 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.4389. Min Act: -0.0001
Data Index: 1320716 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7942. Min Range: -1.7942
Max Act: 1.3855. Min Act: -0.0001
Data Index: 1608450 (Python Code)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19