Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2599 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.5535. Min Act: -0.0001
Data Index: 1551290 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.5086. Min Act: -0.0001
Data Index: 868530 (The Pile)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.5080. Min Act: -0.0001
Data Index: 766165 (The Pile)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.5124. Min Act: -0.0001
Data Index: 293887 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4983. Min Act: -0.0001
Data Index: 359892 (The Pile)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4997. Min Act: -0.0001
Data Index: 1335357 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.5149. Min Act: -0.0001
Data Index: 1669235 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4956. Min Act: -0.0001
Data Index: 1025425 (The Pile)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4487. Min Act: -0.0001
Data Index: 1395982 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4772. Min Act: -0.0001
Data Index: 6990 (The Pile)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4539. Min Act: -0.0001
Data Index: 251419 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4746. Min Act: -0.0001
Data Index: 144902 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4829. Min Act: -0.0001
Data Index: 731567 (The Pile)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4388. Min Act: -0.0001
Data Index: 1131128 (The Pile)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4801. Min Act: -0.0001
Data Index: 1646927 (The Pile)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4878. Min Act: -0.0001
Data Index: 945969 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4805. Min Act: -0.0001
Data Index: 452828 (The Pile)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4642. Min Act: -0.0001
Data Index: 762531 (The Pile)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4462. Min Act: -0.0001
Data Index: 1923617 (The Pile)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5535. Min Range: -0.5535
Max Act: 0.4610. Min Act: -0.0001
Data Index: 944378 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19