Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 398 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0070. Min Act: -0.0003
Data Index: 1948960 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0070. Min Act: -0.0002
Data Index: 116388 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0070. Min Act: -0.0003
Data Index: 1543723 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0070. Min Act: -0.0003
Data Index: 1451379 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0070. Min Act: -0.0002
Data Index: 833076 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0070. Min Act: -0.0002
Data Index: 568536 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0070. Min Act: -0.0003
Data Index: 286373 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0066. Min Act: -0.0002
Data Index: 1397668 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0067. Min Act: -0.0003
Data Index: 195594 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0067. Min Act: -0.0003
Data Index: 1643326 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0067. Min Act: -0.0002
Data Index: 431360 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0066. Min Act: -0.0003
Data Index: 1891269 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0066. Min Act: -0.0003
Data Index: 32424 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0066. Min Act: -0.0002
Data Index: 1602016 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0066. Min Act: -0.0002
Data Index: 1833273 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0066. Min Act: -0.0002
Data Index: 1524339 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0066. Min Act: -0.0003
Data Index: 1934423 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0066. Min Act: -0.0002
Data Index: 463840 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0066. Min Act: -0.0003
Data Index: 1599437 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0070. Min Range: -0.0070
Max Act: 0.0066. Min Act: -0.0002
Data Index: 1530479 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19