Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1383 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.2234. Min Range: -2.2234
Max Act: 2.2234. Min Act: -0.0001
Data Index: 1118036 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2234. Min Range: -2.2234
Max Act: 2.1913. Min Act: -0.0001
Data Index: 649341 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2234. Min Range: -2.2234
Max Act: 2.1930. Min Act: -0.0001
Data Index: 744750 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2234. Min Range: -2.2234
Max Act: 2.1145. Min Act: -0.0001
Data Index: 949070 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.7684. Min Act: -0.0001
Data Index: 1104404 (The Pile)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2234. Min Range: -2.2234
Max Act: 2.0399. Min Act: -0.0001
Data Index: 83020 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2234. Min Range: -2.2234
Max Act: 2.0610. Min Act: -0.0001
Data Index: 446722 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.9307. Min Act: -0.0001
Data Index: 304060 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.7833. Min Act: -0.0001
Data Index: 321806 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.8658. Min Act: -0.0001
Data Index: 1824692 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.8201. Min Act: -0.0001
Data Index: 155682 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.7159. Min Act: -0.0001
Data Index: 219203 (The Pile)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.9051. Min Act: -0.0001
Data Index: 1343376 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.9051. Min Act: -0.0001
Data Index: 78239 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.8047. Min Act: -0.0001
Data Index: 576663 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.9079. Min Act: -0.0001
Data Index: 582913 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.6403. Min Act: -0.0001
Data Index: 508176 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.8213. Min Act: -0.0001
Data Index: 1986903 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.7961. Min Act: -0.0001
Data Index: 1779599 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2234. Min Range: -2.2234
Max Act: 1.7487. Min Act: -0.0001
Data Index: 756292 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19