Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2182 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.5883. Min Act: -0.0000
Data Index: 36870 (The Pile)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.4872. Min Act: -0.0000
Data Index: 1511283 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.5093. Min Act: -0.0000
Data Index: 376995 (The Pile)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.2009. Min Act: -0.0000
Data Index: 395264 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.0900. Min Act: -0.0000
Data Index: 1219502 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.0617. Min Act: -0.0000
Data Index: 1944759 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.0495. Min Act: -0.0000
Data Index: 828568 (The Pile)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.2739. Min Act: 0.0000
Data Index: 1588863 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.1268. Min Act: -0.0000
Data Index: 469047 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.1990. Min Act: -0.0000
Data Index: 676066 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.0475. Min Act: -0.0000
Data Index: 1797089 (The Pile)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5883. Min Range: -2.5883
Max Act: 2.1355. Min Act: -0.0000
Data Index: 503996 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5883. Min Range: -2.5883
Max Act: 1.9871. Min Act: -0.0000
Data Index: 762240 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5883. Min Range: -2.5883
Max Act: 1.8588. Min Act: -0.0000
Data Index: 1057647 (The Pile)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5883. Min Range: -2.5883
Max Act: 1.8137. Min Act: -0.0000
Data Index: 833833 (The Pile)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5883. Min Range: -2.5883
Max Act: 1.8031. Min Act: -0.0000
Data Index: 221585 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5883. Min Range: -2.5883
Max Act: 1.8828. Min Act: -0.0000
Data Index: 1625786 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5883. Min Range: -2.5883
Max Act: 1.7995. Min Act: -0.0000
Data Index: 715089 (The Pile)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5883. Min Range: -2.5883
Max Act: 1.8152. Min Act: -0.0000
Data Index: 99835 (The Pile)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5883. Min Range: -2.5883
Max Act: 1.6842. Min Act: -0.0000
Data Index: 239234 (The Pile)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19