Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1476 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4854. Min Act: -0.0001
Data Index: 815225 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4665. Min Act: -0.0001
Data Index: 1322910 (The Pile)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4935. Min Act: -0.0001
Data Index: 134149 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.3990. Min Act: -0.0001
Data Index: 1914491 (The Pile)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4482. Min Act: -0.0001
Data Index: 658678 (The Pile)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4628. Min Act: -0.0001
Data Index: 1055721 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4378. Min Act: -0.0001
Data Index: 1661948 (The Pile)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4748. Min Act: -0.0001
Data Index: 891917 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4698. Min Act: -0.0001
Data Index: 552193 (The Pile)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4921. Min Act: -0.0001
Data Index: 575039 (The Pile)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4571. Min Act: -0.0001
Data Index: 1824351 (The Pile)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4653. Min Act: -0.0001
Data Index: 243218 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4800. Min Act: -0.0001
Data Index: 1545247 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4793. Min Act: -0.0001
Data Index: 496765 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4431. Min Act: -0.0001
Data Index: 1420469 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.5075. Min Act: -0.0001
Data Index: 663995 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4537. Min Act: -0.0001
Data Index: 57948 (The Pile)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4521. Min Act: -0.0001
Data Index: 1362280 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4231. Min Act: -0.0001
Data Index: 1218776 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5075. Min Range: -0.5075
Max Act: 0.4142. Min Act: -0.0001
Data Index: 1429379 (The Pile)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19