Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 2033 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.4466. Min Act: -0.0000
Data Index: 580858 (The Pile)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.2996. Min Act: 0.0000
Data Index: 569074 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.2574. Min Act: -0.0001
Data Index: 232354 (The Pile)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.2054. Min Act: -0.0001
Data Index: 1573833 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.1227. Min Act: -0.0001
Data Index: 1131889 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.1871. Min Act: 0.0000
Data Index: 1565463 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.1772. Min Act: -0.0000
Data Index: 1466186 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.1413. Min Act: -0.0000
Data Index: 789895 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.1427. Min Act: -0.0000
Data Index: 603620 (The Pile)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.0939. Min Act: -0.0000
Data Index: 314421 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.1121. Min Act: -0.0000
Data Index: 1275789 (The Pile)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.0904. Min Act: -0.0000
Data Index: 128475 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.0971. Min Act: -0.0000
Data Index: 899342 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.0538. Min Act: -0.0000
Data Index: 1445581 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.0254. Min Act: -0.0000
Data Index: 1340282 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4466. Min Range: -1.4466
Max Act: 0.9606. Min Act: -0.0000
Data Index: 1933562 (The Pile)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4466. Min Range: -1.4466
Max Act: 0.9691. Min Act: -0.0001
Data Index: 244847 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.0383. Min Act: -0.0000
Data Index: 924879 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4466. Min Range: -1.4466
Max Act: 0.9519. Min Act: -0.0000
Data Index: 1312525 (The Pile)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4466. Min Range: -1.4466
Max Act: 1.0082. Min Act: -0.0000
Data Index: 849356 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19