Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1862 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.5615. Min Range: -1.5615
Max Act: 1.5615. Min Act: -0.0001
Data Index: 9423 (The Pile)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5615. Min Range: -1.5615
Max Act: 1.1114. Min Act: -0.0001
Data Index: 395728 (The Pile)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5615. Min Range: -1.5615
Max Act: 1.1257. Min Act: -0.0001
Data Index: 376004 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5615. Min Range: -1.5615
Max Act: 1.1306. Min Act: -0.0001
Data Index: 505267 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5615. Min Range: -1.5615
Max Act: 1.0202. Min Act: -0.0001
Data Index: 1894398 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5615. Min Range: -1.5615
Max Act: 1.0152. Min Act: -0.0001
Data Index: 1269320 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5615. Min Range: -1.5615
Max Act: 1.0595. Min Act: -0.0001
Data Index: 1447169 (The Pile)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5615. Min Range: -1.5615
Max Act: 0.9905. Min Act: -0.0001
Data Index: 1008497 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5615. Min Range: -1.5615
Max Act: 0.9514. Min Act: -0.0001
Data Index: 1243133 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5615. Min Range: -1.5615
Max Act: 1.1295. Min Act: -0.0001
Data Index: 1527932 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5615. Min Range: -1.5615
Max Act: 0.7591. Min Act: -0.0001
Data Index: 809735 (The Pile)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5615. Min Range: -1.5615
Max Act: 0.8924. Min Act: -0.0001
Data Index: 42220 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5615. Min Range: -1.5615
Max Act: 0.9522. Min Act: -0.0001
Data Index: 1714877 (The Pile)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5615. Min Range: -1.5615
Max Act: 1.0147. Min Act: -0.0001
Data Index: 738939 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5615. Min Range: -1.5615
Max Act: 0.9626. Min Act: -0.0001
Data Index: 72660 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5615. Min Range: -1.5615
Max Act: 0.9905. Min Act: -0.0001
Data Index: 359499 (The Pile)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5615. Min Range: -1.5615
Max Act: 1.0859. Min Act: -0.0001
Data Index: 620460 (The Pile)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5615. Min Range: -1.5615
Max Act: 0.9564. Min Act: -0.0001
Data Index: 18038 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5615. Min Range: -1.5615
Max Act: 0.8426. Min Act: -0.0001
Data Index: 268890 (The Pile)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5615. Min Range: -1.5615
Max Act: 0.7898. Min Act: -0.0001
Data Index: 1724986 (The Pile)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19